CN115239811A - Positioning method, system, computer and storage medium based on binocular vision detection - Google Patents
Positioning method, system, computer and storage medium based on binocular vision detection Download PDFInfo
- Publication number
- CN115239811A CN115239811A CN202210838493.0A CN202210838493A CN115239811A CN 115239811 A CN115239811 A CN 115239811A CN 202210838493 A CN202210838493 A CN 202210838493A CN 115239811 A CN115239811 A CN 115239811A
- Authority
- CN
- China
- Prior art keywords
- product
- camera
- binocular vision
- products
- positioning method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000001514 detection method Methods 0.000 title claims abstract description 32
- 230000004438 eyesight Effects 0.000 title claims abstract description 31
- 238000001914 filtration Methods 0.000 claims abstract description 12
- 230000000007 visual effect Effects 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 11
- 241001292396 Cirrhitidae Species 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 5
- 230000009977 dual effect Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 claims 2
- 230000007812 deficiency Effects 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a positioning method, a positioning system, a computer and a storage medium based on binocular vision detection, wherein the positioning method comprises the following steps: s1, determining the relative position and posture of a double camera and a robot arm; s2, selecting an initial position; s3, collecting a template sample image; s4, dividing the position (x) of each product i ，y i ) And angle alpha i (ii) a S6, filtering the result obtained by matching in the S5; s7 determining the spatial position (x) i ，y i ，z i ) (ii) a S8 obtaining a positioning position (x) i ，y i ) Coordinate values and angle α i values. The invention adopts a shape matching method, the position data precision data can reach sub-pixels, the brightness and the deficiency of the image are not influenced, and the search angle can be freely set. The invention also utilizes the height information obtained by binocular vision to correctly distinguish products with the same front and back shapes, thereby expanding the application range of the flexible feeding device.
Description
Technical Field
The invention relates to the field of visual positioning, in particular to a positioning method, a positioning system, a computer and a storage medium based on binocular visual detection.
Background
The visual positioning is to transmit the collected real object image to the PLC image processing system through the CCD carried by the machine equipment, calculate the offset position and angle through the image processing positioning software, then feed back to the external platform motion controller, and complete the position deviation rectifying function through the precise servo drive.
The procedure for visual localization is as follows: the installation of the CCD is confirmed, clear imaging can be realized, and the platform can normally run; setting platform parameters and positioning precision according to the platform type; the sample self-learns, corrects, calculates the relative relation of coordinate position between CCD and the platform; shooting a target object; shooting a subject; in the positioning process, the offset distance and the angle are automatically calculated; controlling the platform to move according to the offset value; if the precision is qualified, ending the automatic alignment in the range, otherwise returning to the step of shooting the target object, and continuing to perform automatic alignment adjustment until the precision is qualified.
In the existing visual positioning process, the visual positioning is limited by the constraint between the visions, the effective range of the positioning is limited, the real size and the shape of the product in the limited range cannot be accurately obtained, and the overlapped product or the product with the same positive and negative shapes cannot be correctly distinguished.
Disclosure of Invention
In order to solve the technical problems, the invention provides a positioning method, a positioning system, a computer and a storage medium based on binocular vision detection.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a positioning method based on binocular vision detection comprises the following steps:
s1, calibrating the relative position and posture of a double camera and a robot arm by using a nine-point method;
s2, grabbing a product from the target position and putting the product into the visual field range of the camera to serve as an initial position;
s3, acquiring an image containing a required product as a template sample image from the image shot by the first camera;
s4, spreading a product to be fed on a flexible vibration disc;
s5, shooting by the first cameraPerforming template matching based on shape on the product image shot in the step S4 and the template sample image shot in the step S3, and segmenting the position (x) of each product i ，y i ) And angle alpha i ；
S6, filtering the products with overlapping according to whether the matching result in the S5 is crossed or not;
s7, shooting the product image on the S4 through the second camera, filtering the product image by the first camera in the S6, and intersecting the spatial position (x) of the product with the result space marked by nine points in the S1 i ，y i ，z i )；
S8, z obtained in S7 i The height information is matched with the fixed height information of the placed product, and then the material returning product can be removed, so that the positioning position (x) of the product on the flexible vibration disk is obtained i ，y i ) Coordinate values and angle α i values.
The technical scheme is realized by determining a pixel coordinate system by a camera and a space coordinate system by a mechanical arm, arranging 3 multiplied by 3 points on a plane in a square matrix, respectively walking out coordinates of 9 points by the mechanical arm, simultaneously identifying the pixel coordinates of the 9 points by the camera to obtain 9 corresponding coordinate sets, calculating a coordinate change matrix between the double camera and the mechanical arm by a Halcon nine-point calibration method, accurately associating the pixel coordinate system with the space coordinate system, grabbing an individual product which is a front side and placing the product in a visual field range of the camera, shooting and collecting an image by a first camera to be used as a template sample image and record an initial position, pouring the product on a flexible vibration disc, vibrating the product which is overlapped and attached together and the product which is a back side to the shape of a required loading product, shooting the product on the flexible vibration disc by the first camera and shooting the template sample image which is originally shot by the first camera to be matched in shape to obtain the position (x) of each product i ，y i ) And angle alpha i Filtering out overlapped and attached products according to the result, shooting the product on the flexible vibration disk by the second camera and the product image filtered by the first camera, and intersecting the product in the nine-point calibrated result spaceSpatial position (x) of i ，y i ，z i ) By using z i And matching the height information with the fixed height information of the placed product, and removing the material-returning product, thereby obtaining the position coordinate information of the product capable of being loaded.
As a preferable aspect of the present invention, in the step S1, a coordinate change matrix between the dual camera and the robot arm is calculated by Halcon through a nine-point calibration method.
In a preferred embodiment of the present invention, the first camera is disposed perpendicular to the working plane, and the second camera is disposed obliquely above the working plane.
As a preferable aspect of the present invention, the second camera inclination angle is set to 30 to 60 degrees.
By means of the technical scheme, the inclination angle of the second camera is preferably 45 degrees, and the inclination angle is set to improve the calculation efficiency when the change matrix is calculated and used subsequently.
In a preferable embodiment of the present invention, in the step S5, the angle α is i For each product position (x) i ，y i ) The included angle between the coordinate system and the frame is 0-360 degrees.
The technical scheme is realized, the products are irregularly distributed on the flexible vibration disk, the center of the flexible vibration disk is used for constructing a coordinate system, all the products are contained in four coordinate systems, and the angle alpha is utilized i The direction relation with the coordinate center point is given.
As a preferable aspect of the present invention, in the step S5, when the overlapped products are filtered, when the position coordinates and the angle of the products are compared, a matching threshold is set, and when the position coordinates and the angle of the products are compared, the products are matched as non-overlapped products when the position coordinates and the angle of the products are higher than the threshold, and the products are matched as overlapped or partially crossed products when the position coordinates and the angle of the products are lower than the threshold, and the products are filtered.
Due to the fact that the product has the size, a matching threshold value is needed to be set instead of defining simple coordinates and angle coincidence as overlapping and crossing products.
As a preferable aspect of the present invention, the product position area on the flexible vibration disk irradiated by the first and second cameras is the same as the working area of the robot arm.
In order to achieve the purpose, the invention provides a system based on binocular vision detection, which comprises a mechanical arm, a first camera, a second camera and a flexible vibration disc, wherein the mechanical arm is used for feeding and grabbing a detected product, the first camera and the second camera shoot to obtain an image signal, and the flexible vibration disc is used for placing the product and shaking and scattering the product.
In order to achieve the above purpose, the present invention provides a computer based on binocular vision detection, which comprises an acceptance unit, a detection unit, a processing unit, and a control unit, wherein the acceptance unit is configured to receive image signals of a product acquired by a first camera and a second camera, the image signals form vision positioning data capable of being detected by the detection unit after being accepted, the vision positioning data includes product coordinates, product offset angles, and product heights, the detection unit is first configured to detect whether position coordinates and angles of the product overlap and intersect, and then detect whether the product is a reverse material, the processing unit is configured to send qualified product position information to the control unit after the detection, and the control unit is configured to control the work of a mechanical arm and a flexible vibration disc.
To achieve the above object, the present invention provides a storage medium based on binocular vision detection, storing a program for implementing the positioning method based on binocular vision detection as set forth in claim 1, the storage medium implementing the degree of operation in combination with a system.
In conclusion, the invention has the following beneficial effects: determining a pixel coordinate system by using a camera and a space coordinate system by using a mechanical arm, arranging 3 multiplied by 3 points on a plane in a square matrix, respectively walking out coordinates of 9 points by using the mechanical arm, simultaneously identifying the pixel coordinates of the 9 points by using the camera to obtain 9 corresponding coordinate sets, calculating a coordinate change matrix between the double cameras and the mechanical arm by using a Halcon nine-point calibration method, accurately associating the pixel coordinate system with the space coordinate system, then grabbing an individual product which is a front surface and placing the product in a visual field range of the camera, and shooting and acquiring images by using a first camera to place the image in the visual field range of the cameraPouring products on a flexible vibrating disk as template sample images and recording initial positions, vibrating the products to make the products overlapped and attached together and the products with the reverse side vibrate to the shape of the products to be fed, and then shooting the products on the flexible vibrating disk by a first camera to match the shape of the template sample images shot by the first camera to obtain the position (x) of each product i ，y i ) And angle alpha i Filtering out overlapped and attached products according to the result, shooting the images of the products on the flexible vibration disk and the products filtered out by the first camera by the second camera, and intersecting the spatial position (x) of the products by the nine-point calibrated result space i ，y i ，z i ) By the use of z i And matching the height information with the fixed height information of the placed product, and removing the material-returning product, thereby obtaining the position coordinate information of the product capable of being loaded. The product position data precision of the invention can reach sub-pixel, and the invention has no influence on the brightness and the deletion of the image and has large search angle range. Meanwhile, the invention removes overlapped products based on shape matching by using binocular vision, and correctly distinguishes the products with the same front and back shapes by using height information, thereby improving the detection and positioning precision of the products and expanding the application range of the flexible feeding device.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of the present invention.
The numbers and letters in the figures represent the respective part names:
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
As shown in fig. 1, the present invention is a positioning method based on binocular vision detection: the method comprises the following steps:
s1, calibrating the relative position and the posture of the double cameras and the robot arm by using a nine-point method.
In the step S1, a coordinate change matrix between the double cameras and the mechanical arm is calculated by a nine-point calibration method through Halcon.
The double cameras comprise a first camera and a second camera, the first camera is perpendicular to the working plane, and the second camera is obliquely arranged above the working plane. Wherein the second camera tilt angle is set to 30-60 degrees.
The inclination angle of the second camera is preferably 45 degrees, and the setting of the inclination angle improves the calculation efficiency when the calculation of the change matrix and the subsequent use are performed.
Wherein the product position area on the flexible vibration disk irradiated by the first camera and the second camera is the same as the working area of the mechanical arm.
S2, grabbing a product from the target position and putting the product into the visual field range of the camera to serve as an initial position.
And S3, acquiring an image containing a required product as a template sample image from the image shot by the first camera.
S4, spreading the required feeding product on a flexible vibration disc.
S5, carrying out template matching based on shape on the product image shot by the first camera in the S4 and the template sample image shot in the S3, and segmenting the position (x) of each product i ，y i ) And angle alpha i 。
In step S5, the angle alpha i For each product position (x) i ，y i ) The included angle between the coordinate system and the included angle is 0-360 degrees. The products are randomly distributed on the flexible vibration disk to vibrate flexiblyA coordinate system is established at the center of the movable disc, all products are contained in the four coordinate systems, and the angle alpha is used i The direction relation with the coordinate center point is given.
And S6, filtering the products with the overlapping according to the condition whether the cross exists or not for the result obtained by matching in the S5.
In the step S5, when the overlapped product is filtered, when the position coordinates and the angle of the product are compared, a matching threshold is set, and if the matching threshold is higher than the threshold, the product is matched as a non-overlapped product, and if the matching threshold is lower than the threshold, the product is matched as an overlapped or partially crossed product, and the filtering is performed. Since the product itself has a size, it is necessary to set a matching threshold instead of defining pure coordinates and angular coincidence as an overlap-and-cross product.
S7, shooting the product image on the S4 through the second camera, filtering the product image by the first camera in the S6, and intersecting the spatial position (x) of the product with the result space marked by nine points in the S1 i ，y i ，z i )。
S8, z obtained in S7 i The height information is matched with the fixed height information of the placed product, and the material returning product can be removed, so that the positioning position (x) of the product on the flexible vibration disc is obtained i ，y i ) Coordinate values and angle α i values.
Example two
The invention relates to a binocular vision detection-based system which comprises a mechanical arm, a first camera, a second camera and a flexible vibration disc, wherein the mechanical arm is used for loading and grabbing detected products, the first camera and the second camera shoot to obtain image signals, and the flexible vibration disc is used for placing the products and shaking and scattering the products.
EXAMPLE III
The invention relates to a computer based on binocular vision detection, which comprises a receiving unit, a detecting unit, a processing unit and a control unit, wherein the receiving unit is used for receiving product image signals collected by a first camera and a second camera, the image signals form visual positioning data capable of being detected by the detecting unit after being received, the visual positioning data comprise product coordinates, product deviation angles and product heights, the detecting unit is firstly used for detecting whether the position coordinates and the angles of products are overlapped and crossed and then detecting whether the products are reversed, the processing unit is used for sending qualified product position information to the control unit after the detection is finished, and the control unit is used for controlling the work of a mechanical arm and a flexible vibrating disk.
Example four
The invention relates to a storage medium based on binocular vision detection, which stores a program of a positioning method based on binocular vision detection in the first embodiment, and the storage medium is combined with a system to realize the operation of a degree.
By implementing the embodiment, the beneficial effects of the invention are as follows: determining a pixel coordinate system by a camera and a space coordinate system by a mechanical arm, arranging 3 multiplied by 3 points on a plane in a square matrix, respectively walking out coordinates of 9 points by the mechanical arm, simultaneously identifying the pixel coordinates of the 9 points by the camera to obtain 9 corresponding coordinate sets, calculating a coordinate change matrix between the double camera and the mechanical arm by a Halcon nine-point calibration method, accurately associating the pixel coordinate system with the space coordinate system, then grabbing an independent product which is a front side and placing the independent product in a visual field range of the camera, shooting and acquiring an image by a first camera to be used as a template sample image and record an initial position, pouring the product on a flexible vibration disc, vibrating the product to enable the product with the overlapped and attached back side and the product with the front side to be in the shape of the product to be loaded, shooting the product on the flexible vibration disc by the first camera and the template sample image shot by the first camera to be matched in shape to obtain the position (x) of each product i ，y i ) And angle alpha i Filtering out overlapped and attached products according to the result, shooting the images of the products on the flexible vibration disk and the products filtered by the first camera by the second camera, and intersecting the spatial position (x) of the products by the nine-point calibrated result space i ，y i ，z i ) By the use of z i And matching the height information with the fixed height information of the placed product, and removing the material-returning product, thereby obtaining the position coordinate information of the product capable of being loaded. The product position data precision of the invention can reach sub-pixelAnd the method is not influenced by the brightness and the deficiency of the image, and the search angle range is large. Meanwhile, the invention removes overlapped products based on shape matching by using binocular vision, and correctly distinguishes the products with the same front and back shapes by using height information, thereby improving the detection and positioning precision of the products and expanding the application range of the flexible feeding device.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A positioning method based on binocular vision detection is characterized by comprising the following steps:
s1, calibrating the relative position and posture of a double camera and a robot arm by using a nine-point method;
s2, grabbing a product from the target position and putting the product into the visual field range of the camera to serve as an initial position;
s3, acquiring an image containing a required product as a template sample image from the image shot by the first camera;
s4, spreading a product to be fed on a flexible vibration disc;
s5, performing template matching based on shape on the product image shot by the first camera in the S4 and the template sample image shot by the S3, and segmenting the position (x) of each product i ，y i ) And angle alpha i ；
S6, filtering the products with overlapping according to whether the matching result in the S5 is crossed or not;
s7, shooting the product image on the S4 through the second camera, filtering the product image by the first camera in the S6, and intersecting the spatial position (x) of the product with the result space marked by nine points in the S1 i ，y i ，z i )；
S8, z obtained in S7 i The height information is matched with the fixed height information of the placed product, and then the material returning product can be removed, so that the positioning position (x) of the product on the flexible vibration disk is obtained i ，y i ) Coordinate values and angle α i values.
2. The binocular vision detection-based positioning method of claim 1, wherein in the step S1, a coordinate change matrix between the dual camera and the mechanical arm is calculated by Halcon through a nine-point calibration method.
3. The binocular vision detection based positioning method of claim 1, wherein the first camera is disposed perpendicular to a working plane, and the second camera is disposed obliquely above the working plane.
4. The binocular vision detection-based positioning method of claim 3, wherein the second camera inclination angle is set to 30-60 degrees.
5. The binocular vision detection based positioning method of claim 1, wherein in the step S5, an angle α is i For each product position (x) i ，y i ) The included angle between the coordinate system and the included angle is 0-360 degrees.
6. The binocular vision detection-based positioning method of claim 2, wherein in the step S5, when the overlapped products are filtered, a matching threshold is set when comparing the position coordinates and the angle of the products, and above the threshold, the overlapped products are matched as non-overlapped products, and below the threshold, the overlapped or partially crossed products are matched for filtering.
7. The binocular vision detection based positioning method of claim 1, wherein a product location area on the flexible vibratory pan illuminated by the first and second cameras is the same as a working area of the robotic arm.
8. The utility model provides a system based on binocular vision detects, its characterized in that, it includes arm, first camera, second camera, flexible vibration dish, the arm is used for the product after material loading and detection to snatch, first camera shoots with the second camera and acquires image signal, flexible vibration dish is used for placing the product and shakes the product and scatter.
9. The computer based on binocular vision detection is characterized by comprising a receiving unit, a detecting unit, a processing unit and a control unit, wherein the receiving unit is used for receiving product image signals collected by a first camera and a second camera, the detecting unit is firstly used for detecting whether position coordinates and angles of products are overlapped and crossed or not and then detecting whether the products are reversed or not, the processing unit is used for sending qualified product position information to the control unit after detection, and the control unit is used for controlling the work of a mechanical arm and a flexible vibrating disc.
10. A storage medium based on binocular vision inspection, characterized in that a program implementing the positioning method based on binocular vision inspection according to claim 1 is stored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210838493.0A CN115239811A (en) | 2022-07-15 | 2022-07-15 | Positioning method, system, computer and storage medium based on binocular vision detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210838493.0A CN115239811A (en) | 2022-07-15 | 2022-07-15 | Positioning method, system, computer and storage medium based on binocular vision detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115239811A true CN115239811A (en) | 2022-10-25 |
Family
ID=83673750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210838493.0A Pending CN115239811A (en) | 2022-07-15 | 2022-07-15 | Positioning method, system, computer and storage medium based on binocular vision detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115239811A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116873504A (en) * | 2023-09-08 | 2023-10-13 | 深圳市磐锋精密技术有限公司 | Operation monitoring system for flexible vibration disc feeding mechanism |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107767423A (en) * | 2017-10-10 | 2018-03-06 | 大连理工大学 | A kind of mechanical arm target positioning grasping means based on binocular vision |
| CN108593653A (en) * | 2017-12-31 | 2018-09-28 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of screw classification of view-based access control model and damage detection device and method |
| CN110021006A (en) * | 2018-09-06 | 2019-07-16 | 浙江大学台州研究院 | A kind of device and method whether detection automobile parts are installed |
| CN110555878A (en) * | 2018-05-31 | 2019-12-10 | 上海微电子装备（集团）股份有限公司 | Method and device for determining object space position form, storage medium and robot |
| CN111612837A (en) * | 2020-05-27 | 2020-09-01 | 常州节卡智能装备有限公司 | Material arrangement method and material arrangement equipment |
| CN111951237A (en) * | 2020-08-04 | 2020-11-17 | 上海微亿智造科技有限公司 | Visual appearance detection method |
| CN112132889A (en) * | 2020-08-25 | 2020-12-25 | 中国计量大学 | Soft magnet posture recognition and automatic grabbing method based on binocular vision |
| CN112722764A (en) * | 2020-12-19 | 2021-04-30 | 鸿富晋精密工业（太原）有限公司 | Vibration dish and loading attachment |
| CN113196337A (en) * | 2019-01-09 | 2021-07-30 | 株式会社富士 | Image processing apparatus, working robot, substrate inspection apparatus, and specimen inspection apparatus |
| CN114742705A (en) * | 2022-03-25 | 2022-07-12 | 中国科学院合肥物质科学研究院 | Image splicing method based on halcon |
-
2022
- 2022-07-15 CN CN202210838493.0A patent/CN115239811A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107767423A (en) * | 2017-10-10 | 2018-03-06 | 大连理工大学 | A kind of mechanical arm target positioning grasping means based on binocular vision |
| CN108593653A (en) * | 2017-12-31 | 2018-09-28 | 芜湖哈特机器人产业技术研究院有限公司 | A kind of screw classification of view-based access control model and damage detection device and method |
| CN110555878A (en) * | 2018-05-31 | 2019-12-10 | 上海微电子装备（集团）股份有限公司 | Method and device for determining object space position form, storage medium and robot |
| CN110021006A (en) * | 2018-09-06 | 2019-07-16 | 浙江大学台州研究院 | A kind of device and method whether detection automobile parts are installed |
| CN113196337A (en) * | 2019-01-09 | 2021-07-30 | 株式会社富士 | Image processing apparatus, working robot, substrate inspection apparatus, and specimen inspection apparatus |
| CN111612837A (en) * | 2020-05-27 | 2020-09-01 | 常州节卡智能装备有限公司 | Material arrangement method and material arrangement equipment |
| CN111951237A (en) * | 2020-08-04 | 2020-11-17 | 上海微亿智造科技有限公司 | Visual appearance detection method |
| CN112132889A (en) * | 2020-08-25 | 2020-12-25 | 中国计量大学 | Soft magnet posture recognition and automatic grabbing method based on binocular vision |
| CN112722764A (en) * | 2020-12-19 | 2021-04-30 | 鸿富晋精密工业（太原）有限公司 | Vibration dish and loading attachment |
| CN114742705A (en) * | 2022-03-25 | 2022-07-12 | 中国科学院合肥物质科学研究院 | Image splicing method based on halcon |
Non-Patent Citations (1)
| Title |
|---|
| 李一欣 等: "鸡枞菌锥形削根装置设计", 食品与机械, no. 02, 31 December 2020 (2020-12-31) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116873504A (en) * | 2023-09-08 | 2023-10-13 | 深圳市磐锋精密技术有限公司 | Operation monitoring system for flexible vibration disc feeding mechanism |
| CN116873504B (en) * | 2023-09-08 | 2023-11-24 | 深圳市磐锋精密技术有限公司 | Operation monitoring system for flexible vibration disc feeding mechanism |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110555889B (en) | CALTag and point cloud information-based depth camera hand-eye calibration method | |
| US9604363B2 (en) | Object pickup device and method for picking up object | |
| CN110599541B (en) | Method and device for calibrating multiple sensors and storage medium | |
| US9672630B2 (en) | Contour line measurement apparatus and robot system | |
| CN110580724B (en) | Method and device for calibrating binocular camera set and storage medium | |
| JP6573354B2 (en) | Image processing apparatus, image processing method, and program | |
| US7804996B2 (en) | Method for associating stereo image and three-dimensional data preparation system | |
| US9310317B2 (en) | Automated system and method for tracking and detecting discrepancies on a target object | |
| CN108830906B (en) | Automatic calibration method for camera parameters based on virtual binocular vision principle | |
| CN110926330B (en) | Image processing apparatus, image processing method, and program | |
| CN110570477A (en) | Method, device and storage medium for calibrating relative attitude of camera and rotating shaft | |
| US9215453B2 (en) | Method for calibrating a measurement system and device for carrying out the method | |
| CN110084842B (en) | Servo secondary alignment method and device for robot holder | |
| CN111627072A (en) | Method and device for calibrating multiple sensors and storage medium | |
| JP2010210585A (en) | Model display method in three-dimensional visual sensor, and three-dimensional visual sensor | |
| CN110941462A (en) | System and method for automatically learning product manipulations | |
| JP5322050B2 (en) | Marker three-dimensional position measuring method and system | |
| CN115239811A (en) | Positioning method, system, computer and storage medium based on binocular vision detection | |
| KR101469099B1 (en) | Auto-Camera Calibration Method Based on Human Object Tracking | |
| JP4135556B2 (en) | Video recognition device | |
| WO2021039775A1 (en) | Image processing device, image capturing device, robot, and robot system | |
| CN110646231A (en) | Floor sweeping robot testing method and device | |
| JP4044454B2 (en) | Position measurement using zoom | |
| CN106713960B (en) | A kind of intelligent video monitoring system based on recognition of face | |
| CN107274447B (en) | Depth image acquisition device and depth image acquisition method |
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 |