CN110977939A - Target workpiece identification and positioning system - Google Patents
Target workpiece identification and positioning system Download PDFInfo
- Publication number
- CN110977939A CN110977939A CN201911175421.7A CN201911175421A CN110977939A CN 110977939 A CN110977939 A CN 110977939A CN 201911175421 A CN201911175421 A CN 201911175421A CN 110977939 A CN110977939 A CN 110977939A
- Authority
- CN
- China
- Prior art keywords
- workpiece
- image
- target workpiece
- image acquisition
- acquisition device
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/0093—Program-controlled manipulators co-operating with conveyor means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J13/00—Controls for manipulators
- B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/02—Sensing devices
- B25J19/04—Viewing devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/06—Safety devices
- B25J19/061—Safety devices with audible signals
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/16—Program controls
- B25J9/1656—Program controls characterised by programming, planning systems for manipulators
- B25J9/1664—Program controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Manipulator (AREA)
Abstract
The invention provides a target workpiece identification and positioning system, which comprises a workpiece conveying device, a first image acquisition device, a second image acquisition device, an image identification processing unit, a calculation unit and a control unit, wherein the workpiece conveying device is used for conveying a workpiece to a target workpiece; the workpiece conveying device is used for placing and conveying workpieces; the first image acquisition device is used for acquiring an overlook angle image of the workpiece; the second image acquisition device is used for acquiring a side-view angle image of the workpiece; the image identification processing unit is used for receiving the images acquired by the first image acquisition device and the second image acquisition device, identifying and processing the images and sending the identification processing result to the computing unit; the calculating unit is used for calculating the motion trail of the target workpiece; the control unit is used for controlling the first image acquisition device and the second image acquisition device to acquire images and controlling the robot to work according to the calculated motion track of the target workpiece; the invention can solve the technical problem that the robot cannot accurately identify and position the target workpiece before grabbing the workpiece.
Description
Technical Field
The invention relates to the technical field of machine vision, in particular to a target workpiece identification and positioning system.
Background
One of the most common types of operations performed by industrial robots operating in automated manufacturing lines or in flexible manufacturing systems is the "pick-and-place" action, such as workpiece handling, assembly on a flow line, and workpiece transfer and loading and unloading between stations. In this process, the initial and end poses of the workpiece with respect to the robot are specified in advance; however, in many cases, especially in the pipeline situation, the pose of the workpiece is often not fixed. This results in the actual target workpiece pose always deviating from the ideal workpiece pose, which even if small may result in a robot grabbing failure.
In the prior art, a commonly used technical solution is to install a single or two cameras above a conveyor belt, and to realize the positioning of a workpiece in a manner of a monocular or binocular machine vision recognition system. However, in the technical scheme, the cameras are all arranged right above the conveyor belt, the workpiece can only be shot from a top view angle, and for the workpiece which is irregular in shape and difficult to grasp, the ideal grasping part of the workpiece cannot be well recognized by the image recognition algorithm by using the top view image in the prior art.
The utility model patent of the utility model publication No. CN208622139U discloses a "work piece intelligent identification system based on stereovision", this system uses the CCD camera to carry out all-round the shooing to the work piece, to many images of the work piece each angle of shooing, carries out image recognition processing many times, realizes getting up comparatively complicatedly. The invention patent with application publication number CN106829469A discloses a robot disordered grabbing device and method based on two cameras, wherein a first camera of the device is used for identifying a workpiece, and a second camera is used for adjusting the pose of the workpiece after the robot grabs the workpiece, but the technical problem of accurately identifying and positioning a target workpiece before the robot grabs the workpiece is not solved.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a target workpiece identification and positioning system, which aims to solve the technical problem that a robot in the prior art cannot accurately identify and position a target workpiece before grabbing the workpiece.
The invention adopts the technical scheme that the target workpiece identification and positioning system comprises a workpiece conveying device, a first image acquisition device, a second image acquisition device, an image identification processing unit, a calculation unit and a control unit;
the workpiece conveying device is used for placing and conveying workpieces;
the first image acquisition device is positioned right above the workpiece conveying device in the vertical direction and is used for acquiring an overlook angle image of the workpiece; the second image acquisition device is positioned on the side surface of the workpiece conveying device in the horizontal direction and is used for acquiring side view angle images of the workpiece;
the input end of the image identification processing unit is connected with the first image acquisition device and the second image acquisition device, the output end of the image identification processing unit is connected with the computing unit, and the image identification processing unit is used for receiving the images acquired by the first image acquisition device and the second image acquisition device, identifying and processing the images and sending the identification processing result to the computing unit;
the input end of the computing unit is connected with the image recognition processing unit, and the output end of the computing unit is connected with the control unit; the computing unit is used for computing the motion trail of the target workpiece and transmitting the motion trail to the control unit;
the input end of the control unit is connected with the computing unit, and the output end of the control unit is respectively connected with a first image acquisition device and a second image acquisition device; the control unit is used for controlling the first image acquisition device and the second image acquisition device to acquire images and receiving the motion trail of the target workpiece calculated by the calculation unit.
Further, the calculation unit calculates the motion track of the target workpiece, and the method is realized according to the following steps:
s1, after a target workpiece enters the visual field of an image acquisition device, acquiring a first image of the target workpiece by the image acquisition device;
s2, an image recognition unit obtains space coordinate information of the target workpiece when the first image of the target workpiece is acquired according to the first image of the target workpiece;
s3, the control unit sets a tracking range circle according to the spatial coordinate information in the step S2;
s4, moving the target workpiece along with the workpiece conveying device (1) to enter a space coordinate range of a tracking range circle; the control unit controls the image acquisition equipment to acquire continuous multi-frame images of the target workpiece;
s5, the image recognition processing unit carries out recognition processing according to the continuous multi-frame images to obtain a plurality of pieces of space coordinate information of the target workpiece;
and S6, calculating the motion track of the target workpiece by the calculating unit according to the plurality of spatial coordinate information.
Furthermore, the target workpiece identification and positioning system also comprises a robot, wherein the robot is positioned beside the workpiece conveying device and is connected with the control unit; and the control unit controls the robot to work according to the motion track of the target workpiece calculated by the calculation unit.
Further, the robot is a six-axis industrial robot.
Further, the image recognition processing unit deduces the space coordinate information of the target workpiece in the X axis and the Y axis from the image collected by the first camera according to a Zhang-friend calibration method.
Further, the image recognition processing unit deduces the space coordinate information of the target workpiece in the Z axis from the image collected by the second camera according to a Zhang-friend calibration method.
Furthermore, the target workpiece recognition and positioning system also comprises a third camera, wherein the third camera is positioned on the other side of the conveyor belt opposite to the second camera and is respectively connected with the image recognition processing unit and the control unit.
Furthermore, the target workpiece identification and positioning system also comprises a monitoring alarm unit which is respectively connected with the calculation unit and the control unit; when the appearance change of the target workpiece exceeds a preset value, the monitoring alarm unit gives an alarm and transmits the alarm information to the control unit.
According to the technical scheme, the beneficial technical effects of the invention are as follows:
1. two cameras with different positions are used, and a top view angle image and a side view angle image of a target workpiece can be shot respectively; spatial coordinate information of the workpiece in an X axis and a Y axis can be obtained through overlooking the angle image; the spatial coordinate information of the workpiece in the Z axis can be obtained through the side view angle image. The space coordinate information of the workpiece obtained in the way is more accurate than the space coordinate information derived from the overlooking angle image of the workpiece only by a binocular vision recognition system in the prior art.
2. By setting the tracking range circle and calculating the motion trail of the target workpiece after the target workpiece is tracked, the calculation amount of the target workpiece for identification and positioning can be reduced.
3. Images of the workpiece in three dimensions are shot, and ideal grabbing points of the target workpiece can be better identified and positioned.
4. When the shape change of the target workpiece exceeds a preset value, the robot is controlled not to execute grabbing action on the target workpiece, and invalid grabbing action of the robot is avoided.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
FIG. 1 is a schematic diagram of the system of the present invention.
FIG. 2 is a block diagram of a system architecture according to the present invention.
FIG. 3 is a block diagram of another system architecture of the present invention.
FIG. 4 is a schematic diagram of a reference coordinate system according to the present invention.
Reference numerals:
1-a workpiece conveying device, 2-a first image acquisition device, 3-a second image acquisition device, 4-a robot, 5-an industrial personal computer, 6-a target workpiece, 7-an image acquisition device, a visual field range and 8-a tracking range circle.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
Example 1
As shown in fig. 1 and fig. 2, the present invention provides a target workpiece recognition and positioning system, which comprises a workpiece conveying device 1, a first image acquisition device 2, a second image acquisition device 3, an image recognition processing unit, a calculation unit and a control unit;
the workpiece conveying device 1 is used for placing and conveying workpieces;
the first image acquisition device 2 is positioned right above the workpiece conveying device 1 in the vertical direction and is used for acquiring an overlook angle image of the workpiece; the second image acquisition device 3 is positioned on the side surface of the workpiece conveying device 1 in the horizontal direction and is used for acquiring side view angle images of the workpiece;
the input end of the image identification processing unit is connected with the first image acquisition device 2 and the second image acquisition device 3, the output end of the image identification processing unit is connected with the computing unit, and the image identification processing unit is used for receiving the images acquired by the first image acquisition device 2 and the second image acquisition device 3, identifying and processing the images, and sending the identification processing result to the computing unit;
the input end of the computing unit is connected with the image recognition processing unit, and the output end of the computing unit is connected with the control unit; the computing unit is used for computing the motion trail of the target workpiece and transmitting the motion trail to the control unit;
the input end of the control unit is connected with the computing unit, and the output end of the control unit is respectively connected with the first image acquisition device 2 and the second image acquisition device 3; the control unit is used for controlling the first image acquisition device 2 and the second image acquisition device 3 to acquire images and receiving the motion trail of the target workpiece calculated by the calculation unit.
The target workpiece identification and positioning system also comprises a robot 4, wherein the robot 4 is positioned beside the workpiece conveying device 1 and is connected with the control unit; the control unit controls the robot 4 to work according to the recognition processing result of the image recognition processing unit.
The working principle of example 1 is explained in detail below:
the target workpiece recognition and positioning system is a subsystem in the robot intelligent grabbing system. In the present embodiment, the workpiece conveying device 11 is exemplified by a conveyor belt, the image capturing device is exemplified by a camera, and the image recognition unit, the calculation unit, and the control unit are integrated inside the industrial personal computer 5.
After the robot intelligent grabbing system starts to operate, workpieces are placed on the conveying belt and move in the preset direction along with the transmission of the conveying belt. At the moment, the control unit of the target workpiece recognition and positioning system controls the first camera and the second camera to start working, and image acquisition is carried out in a continuous shooting mode. When the workpiece enters the field of view of the first camera, the first camera captures an overhead angle image of the workpiece. When the workpiece enters the visual field range of the second camera, the second camera can shoot a side view angle image of the workpiece; the second camera may be disposed at a left side of the conveyor belt to photograph a left view of the workpiece; it is also possible to set a right side view of the workpiece taken on the right side of the conveyor belt, which is exemplified by a left side view in the present embodiment.
The first camera and the second camera transmit the shot workpiece images to the image recognition processing unit. The image recognition processing unit may derive a world coordinate system from the pixel coordinate system from the image by using a Zhang-friend scaling method. The specific derivation formula of the Zhangyingyou scaling method is as follows:
in the above formula (1):
the world coordinate system is a coordinate system of a three-dimensional world defined by a user, and is introduced for describing the position of a target object in the real world, and the unit is m;
the camera coordinate system is a coordinate system established on the camera, defined for describing the object position from the camera's perspective, as the middle ring communicating the world coordinate system and the image/pixel coordinate system, in m.
The image physical coordinate system is introduced for describing the projection transmission relation of an object from the camera coordinate system to the image coordinate system in the imaging process, so that the coordinates under the pixel coordinate system can be further conveniently obtained, and the unit is m.
The image pixel coordinate system is introduced for describing coordinates of an image point on a digital image after an object is imaged, and is a coordinate system in which information actually read from a camera is located, and the unit is one (pixel number).
The image recognition processing unit can obtain the actual space coordinate information of the workpiece through the pose information of the workpiece in the image. Specifically, as shown in fig. 4, in the present embodiment, the X axis defining the world coordinate system coincides with the center line of the conveyor belt, and the direction points to the target moving direction; the Y-axis points to the side of the robot 4 and the Z-axis is directed upwards perpendicular to the conveyor plane. The spatial coordinate information of the workpiece in the X axis and the Y axis can be obtained from the image collected by the first camera positioned right above the vertical direction of the conveyor belt; from the image acquired by the second camera located on the horizontal side of the conveyor belt, the spatial coordinate information of the workpiece in the Z-axis can be derived. The space coordinate information of the workpiece obtained in the way is more accurate than the space coordinate information derived from the overlooking angle image of the workpiece only by a binocular vision recognition system in the prior art.
Transmitting the space coordinate information of the target workpiece obtained by the image recognition processing unit to a calculating unit, and calculating the motion trail of the target workpiece, wherein the method is realized by the following steps:
(1) after the target workpiece enters the field of view of the camera, the camera captures a first image of the target workpiece 6. In the present embodiment, preferably, as shown in fig. 4, after the target workpiece 6 enters 7 the field of view of the first camera, the first camera captures a first overhead view image of the target workpiece;
(2) the first image of the target workpiece 6 is transmitted to an image recognition processing unit, and the image recognition processing unit deduces space coordinate information of the target workpiece 6 when the first image is acquired according to a Zhang-Yongyou calibration method;
(3) the control unit sets a tracking range circle according to the spatial coordinate information of the target workpiece 6 when the first image is acquired, as shown in fig. 4, the center of the tracking range circle is located on the X axis.
(4) The target workpiece 6 moves along with the conveyor belt and enters a space coordinate range of a tracking range circle; the control unit controls the camera to shoot continuous multi-frame images of the target workpiece;
(5) the image recognition processing unit carries out recognition processing according to continuous multi-frame images of the target workpiece to obtain a plurality of pieces of space coordinate information of the target workpiece;
(6) the calculation unit calculates the motion trail of the target workpiece according to the plurality of pieces of space coordinate information.
In this embodiment, the motion state of the conveyor belt is uniform linear motion, so that a trajectory equation can be written by only calculating the speed and the position of the target workpiece. The space coordinate of the position of the target workpiece can be obtained by using a Zhang Yongyou scaling method through continuous multi-frame images of the shot target workpiece. The speed of the target workpiece can be obtained by the displacement of the target workpiece in the moving direction, and dividing the time for the target workpiece to complete the displacement; specifically, for example: two images separated by 10 images can be taken in the camera view field, the displacement of the target workpiece in the motion direction is calculated, and the time for shooting the 10 images is divided, so that the speed of the target workpiece can be obtained. By setting the tracking range circle and calculating the motion trail of the target workpiece after the target workpiece is tracked, the calculation amount of the target workpiece for identification and positioning can be reduced.
Meanwhile, the invention shoots the three-dimensional images of the workpiece, so that the ideal grabbing point of the workpiece can be better identified. For the workpiece with an irregular shape, such as a gourd-shaped workpiece, if the robot 4 grabs the round spherical part of the gourd, the robot is easy to slip, so that the grabbing failure is caused, and the ideal grabbing point of the gourd-shaped workpiece is the inward concave part in the middle of the gourd. In the actual production process, if the bottom of the hoist is vertically arranged on the conveyor belt to be conveyed, the camera above the conveyor belt cannot shoot the image of the inward sunken part in the middle of the hoist; in addition, the different vertical inclinations of the hoists can affect the success rate of the robot 4 in grabbing. The second camera is arranged on the side face of the conveyor belt, so that the position of the inward recess in the middle of the hoist can be clearly reflected in a space coordinate system. By shooting the position of the inward sunken part in the middle of the hoist, the image recognition processing unit can recognize and process the position to obtain the space coordinate information of the position; the spatial coordinate information is transmitted to a computing unit, and more accurate input is provided for inverse kinematics solution of the robot 4 in the grabbing process. Therefore, before the robot 4 grabs the workpiece, the ideal grabbing point of the target workpiece can be accurately identified and positioned.
In the embodiment 1, acA2500-14gm of Basler company can be selected as the camera, the image recognition processing function of the image recognition processing unit is programmed and developed by OpenCV and HALCON, the control unit can be selected from the Tuhua IPC-610H industrial personal computer system, and the robot can be selected from an ABB six-axis industrial robot.
Example 2
For some irregularly shaped workpieces, it may occur that there is no ideal gripping point on the side of the workpiece facing the second camera, due to the different poses of the conveyor belts. Thus, if an image is taken only from the left or right side of the workpiece, it is not convenient to find an ideal grasping point of the workpiece using the image recognition technique.
In order to solve the above technical problem, the method is further optimized based on embodiment 1, and a third camera is arranged on the other side of the conveyor belt facing the second camera, and the third camera is respectively connected with the image recognition processing unit and the control unit. The third camera shoots the workpiece image under the control of the control unit and transmits the image to the image recognition processing unit. The second camera and the third camera respectively acquire the left view and the right view of the workpiece and are matched with the workpiece top view acquired by the first camera, so that whether the ideal grabbing point of the workpiece is on the top surface, the left surface or the right surface of the workpiece, the workpiece can be accurately identified through the technical scheme of the invention, and the accurate identification and positioning of the ideal grabbing point of the target workpiece can be further improved on the basis of embodiment 1.
Example 3
For some workpieces with damaged appearance structures, the ideal gripping point of the workpiece is already damaged, and the robot 4 may fail to grip at any angle. In order to reduce the ineffective grabbing action of the robot, the system is further optimized on the basis of the embodiment 1, and a monitoring alarm unit is integrated in the system as shown in fig. 3; the monitoring alarm unit is a developed software module and is matched with a target workpiece identification and positioning system for use. The monitoring alarm unit is respectively connected with the calculation unit and the control unit.
When the shape of the target workpiece varies beyond the preset value, the preset value is 20% out of dimension in the present embodiment. The image acquisition device acquires the image of the workpiece, the image recognition processing unit obtains the appearance change value of the target workpiece, the calculation unit calculates the judgment result of whether the appearance change value exceeds the preset value, and the result is sent to the monitoring alarm unit. If the judgment result is that the preset value is exceeded, the monitoring alarm unit carries out alarm prompt, for example, an alarm sound sending mode is adopted. The purpose of the alarm is to remind an operator on duty to check the abnormal condition of the workpiece. The monitoring alarm unit sends alarm information to the control unit, and the control unit controls the robot 4 not to perform grabbing action on the target workpiece after receiving the information.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (8)
1. A target workpiece recognition and positioning system is characterized in that: the device comprises a workpiece conveying device (1), a first image acquisition device (2), a second image acquisition device (3), an image recognition processing unit, a calculation unit and a control unit; the workpiece conveying device (1) is used for placing and conveying workpieces;
the first image acquisition device (2) is positioned right above the workpiece conveying device (1) in the vertical direction and is used for acquiring an overlook angle image of the workpiece; the second image acquisition device (3) is positioned on the side surface of the workpiece conveying device (1) in the horizontal direction and is used for acquiring side view angle images of the workpiece;
the input end of the image identification processing unit is connected with the first image acquisition device (2) and the second image acquisition device (3), the output end of the image identification processing unit is connected with the computing unit, and the image identification processing unit is used for receiving images acquired by the first image acquisition device (2) and the second image acquisition device (3), identifying and processing the images, and sending an identification processing result to the computing unit;
the input end of the computing unit is connected with the image recognition processing unit, and the output end of the computing unit is connected with the control unit; the computing unit is used for computing the motion trail of the target workpiece and transmitting the motion trail to the control unit;
the input end of the control unit is connected with the computing unit, and the output end of the control unit is respectively connected with a first image acquisition device (2) and a second image acquisition device (3); the control unit is used for controlling the first image acquisition device (2) and the second image acquisition device (3) to acquire images and receiving the motion trail of the target workpiece calculated by the calculation unit.
2. The target workpiece recognition and positioning system of claim 1, wherein: the calculation unit calculates the motion trail of the target workpiece and is realized according to the following steps:
s1, after a target workpiece enters the visual field of an image acquisition device, acquiring a first image of the target workpiece by the image acquisition device;
s2, the image identification unit obtains space coordinate information of the target workpiece when the first image of the target workpiece is acquired according to the first image of the target workpiece;
s3, the control unit sets a tracking range circle according to the space coordinate information in the step S2;
s4, moving the target workpiece along with the workpiece conveying device (1) to enter a space coordinate range of a tracking range circle; the control unit controls the image acquisition equipment to acquire continuous multi-frame images of the target workpiece;
s5, the image recognition processing unit carries out recognition processing according to the continuous multi-frame images to obtain a plurality of pieces of space coordinate information of the target workpiece;
and S6, the calculation unit calculates the motion track of the target workpiece according to the plurality of spatial coordinate information.
3. The target workpiece recognition and positioning system of claim 1, wherein: the automatic feeding device is characterized by further comprising a robot (4), wherein the robot (4) is located beside the workpiece conveying device (1) and connected with the control unit; and the control unit controls the robot (4) to work according to the motion trail of the target workpiece calculated by the calculation unit.
4. The target workpiece recognition and positioning system of claim 3, wherein: the robot (4) is a six-axis industrial robot.
5. The target workpiece recognition and positioning system of claim 2, wherein: and the image recognition processing unit deduces the spatial coordinate information of the target workpiece in the X axis and the Y axis from the image acquired by the first camera according to a Zhang-Yongyou calibration method.
6. The target workpiece recognition and positioning system of claim 2, wherein: and the image recognition processing unit deduces the space coordinate information of the target workpiece in the Z axis from the image acquired by the second camera according to a Zhang-friend calibration method.
7. The target workpiece recognition and positioning system of claim 1, wherein: the device also comprises a third camera, wherein the third camera is positioned on the other side of the workpiece conveying device (1) opposite to the second camera and is respectively connected with the image recognition processing unit and the control unit.
8. The target workpiece recognition and positioning system of claim 1, wherein: the monitoring and alarming unit is respectively connected with the computing unit and the control unit; and when the appearance change of the target workpiece exceeds a preset value, the monitoring alarm unit gives an alarm and transmits the alarm information to the control unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911175421.7A CN110977939B (en) | 2019-11-26 | 2019-11-26 | Target workpiece identification and positioning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911175421.7A CN110977939B (en) | 2019-11-26 | 2019-11-26 | Target workpiece identification and positioning system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110977939A true CN110977939A (en) | 2020-04-10 |
| CN110977939B CN110977939B (en) | 2021-05-04 |
Family
ID=70087157
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911175421.7A Expired - Fee Related CN110977939B (en) | 2019-11-26 | 2019-11-26 | Target workpiece identification and positioning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110977939B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651297A (en) * | 2020-11-23 | 2021-04-13 | 北京旷视机器人技术有限公司 | Warehouse entry management method and device, warehouse management system and electronic system |
| CN114049317A (en) * | 2021-11-03 | 2022-02-15 | 安徽灿宇光电科技有限公司 | CCD equipment automatic inspection system and method based on artificial intelligence |
| CN114619429A (en) * | 2022-04-24 | 2022-06-14 | 广东天太机器人有限公司 | Mechanical arm control method based on recognition template |
| US11383380B2 (en) * | 2013-03-15 | 2022-07-12 | Intrinsic Innovation Llc | Object pickup strategies for a robotic device |
| CN114800484A (en) * | 2021-01-28 | 2022-07-29 | 精工爱普生株式会社 | Robot system control method and robot system |
| CN116824162A (en) * | 2022-03-17 | 2023-09-29 | 中移(上海)信息通信科技有限公司 | Transport belt monitoring methods, devices and related equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6161955B2 (en) * | 1976-07-02 | 1986-12-27 | Hitachi Ltd | |
| CN103692447A (en) * | 2013-12-27 | 2014-04-02 | 西安航天精密机电研究所 | EV (electric vehicle) battery positioning method based on overlook and side-view cameras |
| CN104511436A (en) * | 2013-09-28 | 2015-04-15 | 沈阳新松机器人自动化股份有限公司 | Express sorting method and system based on robot visual servo technology |
| CN107716325A (en) * | 2017-09-30 | 2018-02-23 | 浙江瀚镪自动化设备股份有限公司 | A kind of product intelligent compartment system and method |
| CN108089544A (en) * | 2017-12-25 | 2018-05-29 | 厦门大学嘉庚学院 | A kind of orbit generation method and control system of sole glue spraying robot |
| CN108932363A (en) * | 2017-05-26 | 2018-12-04 | 发那科株式会社 | Shape recognition device, shape recognition process and computer-readable medium |
| CN109366501A (en) * | 2018-12-13 | 2019-02-22 | 中国石油大学(华东) | Air ice hockey robot control method, device and air ice hockey sports equipment |
-
2019
- 2019-11-26 CN CN201911175421.7A patent/CN110977939B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6161955B2 (en) * | 1976-07-02 | 1986-12-27 | Hitachi Ltd | |
| CN104511436A (en) * | 2013-09-28 | 2015-04-15 | 沈阳新松机器人自动化股份有限公司 | Express sorting method and system based on robot visual servo technology |
| CN103692447A (en) * | 2013-12-27 | 2014-04-02 | 西安航天精密机电研究所 | EV (electric vehicle) battery positioning method based on overlook and side-view cameras |
| CN108932363A (en) * | 2017-05-26 | 2018-12-04 | 发那科株式会社 | Shape recognition device, shape recognition process and computer-readable medium |
| CN107716325A (en) * | 2017-09-30 | 2018-02-23 | 浙江瀚镪自动化设备股份有限公司 | A kind of product intelligent compartment system and method |
| CN108089544A (en) * | 2017-12-25 | 2018-05-29 | 厦门大学嘉庚学院 | A kind of orbit generation method and control system of sole glue spraying robot |
| CN109366501A (en) * | 2018-12-13 | 2019-02-22 | 中国石油大学(华东) | Air ice hockey robot control method, device and air ice hockey sports equipment |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11383380B2 (en) * | 2013-03-15 | 2022-07-12 | Intrinsic Innovation Llc | Object pickup strategies for a robotic device |
| CN112651297A (en) * | 2020-11-23 | 2021-04-13 | 北京旷视机器人技术有限公司 | Warehouse entry management method and device, warehouse management system and electronic system |
| CN114800484A (en) * | 2021-01-28 | 2022-07-29 | 精工爱普生株式会社 | Robot system control method and robot system |
| CN114800484B (en) * | 2021-01-28 | 2023-06-02 | 精工爱普生株式会社 | Control method of robot system and robot system |
| CN114049317A (en) * | 2021-11-03 | 2022-02-15 | 安徽灿宇光电科技有限公司 | CCD equipment automatic inspection system and method based on artificial intelligence |
| CN116824162A (en) * | 2022-03-17 | 2023-09-29 | 中移(上海)信息通信科技有限公司 | Transport belt monitoring methods, devices and related equipment |
| CN114619429A (en) * | 2022-04-24 | 2022-06-14 | 广东天太机器人有限公司 | Mechanical arm control method based on recognition template |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110977939B (en) | 2021-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110977939B (en) | Target workpiece identification and positioning system | |
| US10442633B2 (en) | Robot system | |
| CN110509281B (en) | Binocular vision-based pose recognition and grabbing device and method | |
| CN107150032B (en) | Workpiece identification and sorting device and method based on multi-image acquisition equipment | |
| CN107972026B (en) | Robot, mechanical arm and control method and device thereof | |
| CN109665307B (en) | Work system, work execution method for article, and robot | |
| CN107618030B (en) | Robot dynamic tracking grabbing method and system based on vision | |
| US10232512B2 (en) | Coordinate system setting method, coordinate system setting apparatus, and robot system provided with coordinate system setting apparatus | |
| CN110497401B (en) | Robot system for taking out bulk work and control method of robot system | |
| JP4565023B2 (en) | Article take-out device | |
| US20190193947A1 (en) | Article transfer apparatus, robot system, and article transfer method | |
| CN110980276B (en) | A method for automatic blanking of castings with three-dimensional vision and robots | |
| US10521871B2 (en) | Robot system | |
| CN212284935U (en) | Sheet metal sorting device based on 3D vision | |
| WO2021053750A1 (en) | Work robot and work system | |
| CN106272424A (en) | A kind of industrial robot grasping means based on monocular camera and three-dimensional force sensor | |
| CN106334739A (en) | A flexible intelligent stamping system | |
| CN108177150A (en) | Door of elevator positioning and grabbing device and the method for view-based access control model | |
| CN104626169A (en) | Robot part grabbing method based on vision and mechanical comprehensive positioning | |
| JP2019005856A (en) | Robot system | |
| CN114405865A (en) | Vision-guided steel plate sorting method, vision-guided steel plate sorting device and system | |
| CN118752514A (en) | A robot end clamping mechanism | |
| CN115319762B (en) | Robot control method for production line, production line and numerical control machine tool | |
| JP5428921B2 (en) | Work collection device and method from hanger line | |
| JP6697510B2 (en) | Robot system |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210504 Termination date: 20211126 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |