CN111815634A - Machine vision-based memory alignment plug-in method, system, equipment and storage medium - Google Patents
Machine vision-based memory alignment plug-in method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN111815634A CN111815634A CN202010940989.XA CN202010940989A CN111815634A CN 111815634 A CN111815634 A CN 111815634A CN 202010940989 A CN202010940989 A CN 202010940989A CN 111815634 A CN111815634 A CN 111815634A
- Authority
- CN
- China
- Prior art keywords
- memory
- state
- mechanical arm
- memory bank
- calculating
- 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 49
- 238000003780 insertion Methods 0.000 claims abstract description 24
- 230000037431 insertion Effects 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims description 33
- 238000005516 engineering process Methods 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 11
- 239000011159 matrix material Substances 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a machine vision-based memory alignment plugging method, a system, equipment and a storage medium, wherein the method comprises the following steps: driving a mobile camera to move to an initial position through a mechanical arm, and acquiring an initial state of a memory bank; moving the mechanical arm to a grabbing position to grab the memory bank according to the deviation value of the initial bit state of the memory bank and the grabbing reference bit state; moving the mechanical arm to a photographing position of a fixed camera, calculating the post-grabbing position state of the memory bank, and moving the mechanical arm to a position to be assembled according to the deviation value of the post-grabbing position state of the memory bank and the assembly reference position state; acquiring an image of the memory slot, calculating the current bit state of the memory slot, and calculating a compensation bit state according to the insertion reference bit state of the memory slot and the current bit state; and calculating the current plug-in position according to the position to be assembled and the compensation position, and moving the mechanical arm to the current plug-in position to perform the memory bank plug-in operation. The invention can improve the operation efficiency of memory plugging, ensure the memory bank and the memory slot to be aligned accurately and prevent collision accidents in the plugging operation process.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a machine vision-based memory alignment plugging method. The invention also relates to a machine vision-based memory alignment plugging system, equipment and a storage medium.
Background
With the development of the electronic technology in China, more and more electronic devices have been widely used.
Servers are important components in electronic devices, and are devices that provide computing services. Since the server needs to respond to and process the service request, the server generally has the capability of assuming and securing the service. The server is divided into a file server, a database server, an application program server, a WEB server and the like according to different service types provided by the server.
In the big data era, a large number of IT devices are centrally located in a data center. These data centers include various types of servers, storage, switches, and a large number of cabinets and other infrastructure. Each IT device is composed of various hardware board cards, such as a computing module, a memory module, a storage module, a chassis and the like. The memory module is one of the important components in a computer, and is a bridge for the communication between the memory module and the CPU. All programs in the computer are executed in the memory, so the performance of the memory has a great influence on the computer. The memory is also an essential component in the server architecture and is in a large number.
At present, in mass production operation of a production line, memory banks need to be inserted into memory slots to complete memory plug-in operation. In the prior art, the memory bank and the memory slot are generally inserted manually by a memory mounting fixture. However, because the main board is installed at a high density, the memory banks are installed in a large number and are generally fully matched for operation, so that the manual operation efficiency is low, the plugging operation wastes time and labor, the labor intensity of workers is high, and the hands are easily injured. Moreover, when the number of the memory banks is large, the memory banks and the memory slots are prone to inaccurate alignment due to external environmental influences, such as vibration, during assembly, and then the memory banks collide with the slot walls of the memory slots during the plug-in mounting, so that the golden fingers of the memory banks are damaged or broken, and the memory slots are damaged.
Therefore, how to improve the operation efficiency of memory insertion, ensure the accurate alignment between the memory bank and the memory slot, and prevent the occurrence of collision accidents in the insertion operation process is a technical problem faced by technical personnel in the field.
Disclosure of Invention
The invention aims to provide a machine vision-based memory alignment and plugging method, which can improve the operation efficiency of memory plugging, ensure that a memory bank and a memory slot are aligned accurately and prevent collision accidents in the plugging operation process. The invention also aims to provide a machine vision-based memory alignment patching system.
In order to solve the technical problem, the invention provides a machine vision-based memory alignment plugging method, which comprises the following steps:
driving a mobile camera to move to an initial position through a mechanical arm, and enabling the mobile camera to obtain an initial position state of a memory bank through an image processing technology;
calculating the offset of the mechanical arm according to the deviation value of the initial position state and the grabbing reference position state of the memory bank, and moving the mechanical arm to a grabbing position according to the offset to grab the memory bank;
moving the mechanical arm to a photographing position of a fixed camera, calculating a post-grabbing bit state of the memory bank through an image processing technology, and moving the mechanical arm to a position to be assembled according to a deviation value of the post-grabbing bit state and an assembly reference bit state;
acquiring images of the memory slots through the mobile camera, calculating the current bit state of the memory slots through an image processing technology, and calculating a compensation bit state according to the current bit state and the plug-in reference bit state of the memory slots;
and calculating the current plug-in mounting position state according to the position to be assembled and the compensation position state, and moving the mechanical arm to the current plug-in mounting position to perform the memory bank plug-in mounting operation.
Preferably, before the moving camera is moved to the initial position synchronously by the mechanical arm, the method further comprises:
and calibrating the coordinates of the photographed images of the mobile camera and the fixed camera and the position coordinates of the mechanical arm to obtain the coordinate conversion relationship between the images of the mobile camera and the mechanical arm and the coordinate conversion relationship between the images of the fixed camera and the mechanical arm.
Preferably, the method for acquiring the initial bit state of the memory bank by the mobile camera through the image processing technology specifically includes:
and enabling the mobile camera to acquire the contour of the memory bank in a preset ROI (region of interest) through a connected domain analysis method, fitting an edge contour line of the memory bank through a straight line, and calculating the initial state of the memory bank according to the edge contour line.
Preferably, before obtaining the initial bit state of the memory bank, the method further includes:
and acquiring a grabbing reference position state of the mechanical arm, an assembling reference position state of the memory bank and an inserting reference position state of the memory slot.
Preferably, the acquiring of the grabbing reference position state of the mechanical arm specifically includes:
driving the mobile camera to move to a photographing reference position state capable of acquiring the memory bank image through the mechanical arm;
acquiring an image of the memory bank through the mobile camera and calculating a first coordinate reference bit state of the memory bank;
and grabbing the memory bank through the mechanical arm, and vertically ascending for a preset distance to a grabbing reference position state.
Preferably, the obtaining of the assembly reference state of the memory bank specifically includes:
the memory bank is held and grabbed by the mechanical arm and is moved to a photographing position of the fixed camera;
and acquiring the image of the memory bank through the fixed camera and calculating the assembly reference bit state of the memory bank.
Preferably, the obtaining of the plug-in reference bit state of the memory slot specifically includes:
driving the mobile camera to move to an identification reference position state capable of acquiring the memory slot image through the mechanical arm;
acquiring an image of the memory slot through the mobile camera and calculating a second coordinate reference position state of the memory slot;
and driving the mobile camera to move to an insertion reference position state with a preset distance above the memory slot through the mechanical arm.
The invention also provides a machine vision-based memory alignment plugging system, which comprises:
the initial acquisition module is used for driving the mobile camera to move to an initial position through the mechanical arm and enabling the mobile camera to acquire the initial state of the memory bank through an image processing technology;
the memory grabbing module is used for calculating the offset of the mechanical arm according to the deviation value of the initial bit state and the grabbing reference bit state of the memory bank, and moving the mechanical arm to a grabbing position to grab the memory bank according to the offset;
the attitude adjusting module is used for moving the mechanical arm to a photographing position of a fixed camera, calculating a post-grabbing bit state of the memory bank through an image processing technology, and moving the mechanical arm to a position to be assembled according to a deviation value of the post-grabbing bit state and an assembling reference bit state;
the slot positioning module is used for acquiring images of the memory slots through the mobile camera, calculating the current bit state of the memory slots through an image processing technology, and calculating a compensation bit state according to the current bit state and the plug-in reference bit state of the memory slots;
and the alignment insertion module is used for calculating the current insertion position state according to the position to be assembled and the compensation position state and moving the mechanical arm to the current insertion position to perform memory bank insertion operation.
The present invention also provides an electronic device comprising:
a memory for storing a computer program;
a processor, configured to implement the steps of the machine vision memory-based alignment plugging method according to any one of the above descriptions when the computer program is executed.
The invention further provides a storage medium, wherein a computer program is stored on the storage medium, and when being executed by a processor, the computer program realizes the steps of the machine vision memory alignment-based patching method.
The machine vision-based memory alignment plugging method mainly comprises five steps. In the first step, the mobile camera is driven to move to an initial position by the motion of the mechanical arm, and then the mobile camera acquires the initial state (the state includes position and posture) of the memory bank by an image processing technology. In the second step, deviation value calculation is carried out according to the calculated initial position state of the memory bank and a preset grabbing reference position state to obtain the offset of the mechanical arm, and then the mechanical arm is moved to a grabbing position according to the offset to grab the memory bank. In the third step, the mechanical arm is moved to the memory slot after the memory bank is grabbed, the memory slot is located in the area where the fixed camera is located, the mechanical arm is moved to the photographing position of the fixed camera, the grabbed position state of the memory bank is calculated through the fixed camera by using an image processing technology, deviation value calculation is performed according to the grabbed position state of the memory bank and a preset assembly reference position state, and the mechanical arm is moved to the position to be assembled according to the deviation value. In the fourth step, in order to determine the bit state of the current memory slot, firstly, the memory slot is subjected to image acquisition by the mobile camera, then, the current bit state of the memory slot is calculated by utilizing an image processing technology, and then, the compensation bit state is calculated according to the deviation value of the current bit state and the preset insertion reference bit state. In the fifth step, the final inserting position state can be calculated according to the position to be assembled and the compensation position state, and then the mechanical arm is moved to the inserting position to perform the inserting operation of the memory bank. Therefore, the machine vision-based memory alignment and plugging method provided by the invention has the advantages that the mechanical arm, the memory bank and the memory slot are subjected to image acquisition through the mobile camera and the fixed camera, the coordinate bit states of the mechanical arm, the memory bank and the memory slot are calculated by using an image processing technology, the mechanical arm is guided to move by correcting the deviation value between the real-time bit state and the preset reference bit state in the plug-in operation process of the memory bank, and finally, the bit state compensation of the memory slot is introduced, so that the memory bank is kept aligned with the memory slot before being plugged. Therefore, the invention can improve the operation efficiency of memory plugging, ensure the memory bank and the memory slot to be aligned accurately and prevent collision accidents in the plugging operation process.
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 embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method according to an embodiment of the present invention.
Fig. 2 is a system structure diagram of an embodiment of the present invention.
Wherein, in fig. 2:
the system comprises an initial acquisition module-1, a memory grabbing module-2, an attitude adjusting module-3, a slot positioning module-4 and an alignment plug-in module-5.
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.
Referring to fig. 1, fig. 1 is a schematic overall structure diagram of an embodiment of the present invention.
In a specific embodiment provided by the present invention, the machine vision-based memory alignment patch method mainly includes five steps, which are respectively:
s1, driving the mobile camera to move to an initial position through the mechanical arm, and enabling the mobile camera to obtain the initial state of the memory bank through an image processing technology;
s2, calculating the offset of the mechanical arm according to the deviation value of the initial position state and the grabbing reference position state of the memory bank, and moving the mechanical arm to the grabbing position according to the offset to grab the memory bank;
s3, moving the mechanical arm to a photographing position of a fixed camera, calculating a post-grabbing state of the memory bank through an image processing technology, and moving the mechanical arm to a position to be assembled according to a deviation value of the post-grabbing state and an assembling reference state;
s4, acquiring images of the memory slots through the mobile camera, calculating the current bit state of the memory slots through an image processing technology, and calculating a compensation bit state according to the current bit state and the insertion reference bit state of the memory slots;
and S5, calculating the current insertion position according to the position to be assembled and the compensation position, and moving the mechanical arm to the current insertion position to perform memory bank insertion operation.
In step S1, since the mobile camera is disposed on the robot arm, the mobile camera can be driven by the motion of the robot arm to move to an initial position, and then the mobile camera obtains the initial state (state including position and posture) of the memory bank through an image processing technique.
In step S2, a deviation value is calculated according to the calculated initial state of the memory bank and a preset capture reference state to obtain an offset of the robot arm, and then the robot arm is moved to a capture position according to the offset to capture the memory bank.
In step S3, the mechanical arm needs to move to the memory slot after capturing the memory bank, and the memory slot is located in the area where the fixed camera (fixed) is located, so that the mechanical arm is moved to the photographing position of the fixed camera, then the post-capture state of the memory bank is calculated by the fixed camera using the image processing technology, a deviation value is calculated according to the post-capture state of the memory bank and the preset assembly reference state, and the mechanical arm is moved to the position to be assembled according to the deviation value.
In step S4, to determine the bit state of the current memory slot, the mobile camera first obtains an image of the memory slot, then calculates the current bit state of the memory slot by using an image processing technique, and then calculates the compensation bit state according to a deviation value between the current bit state and a preset insertion reference bit state.
In step S5, a final insertion position state may be calculated according to the position to be assembled and the compensation position state, and then the mechanical arm is moved to the insertion position to perform the memory bank insertion operation.
Therefore, in the machine vision-based memory alignment and plugging method provided by this embodiment, the mechanical arm, the memory bank, and the memory slot are subjected to image acquisition by the mobile camera and the fixed camera, the coordinate bit states of the mechanical arm, the memory bank, and the memory slot are calculated by using an image processing technology, the mechanical arm is guided to move by correcting the deviation value between the real-time bit state and the preset reference bit state in the process of the memory bank plugging operation, and finally, the bit state compensation of the memory slot is introduced, so that the memory bank is aligned with the memory slot before being plugged. Therefore, the embodiment can improve the operation efficiency of the memory plugging, ensure that the memory bank and the memory slot are aligned accurately, and prevent the occurrence of collision accidents in the plugging operation process.
In addition, in consideration of the fact that the coordinates of the mechanical arm can be accurately positioned according to a space coordinate system constructed by the driving mechanism of the mechanical arm, and the coordinate positioning mode of the mobile camera and the fixed camera for the memory bank can be obtained only by photographing and calculating an image processing technology, in this way, in order to facilitate the mobile camera and the fixed camera to determine the coordinate state of the memory bank through an image acquisition mode, in this embodiment, a calibration flow is first performed before the memory bank is subjected to insertion operation. The calibration process is mainly used for determining the conversion relation between the coordinates of the mechanical arm and the coordinates of images shot by the mobile camera and the fixed camera according to actual equipment and environment.
Specifically, in the calibration process, the mobile camera can adopt an Eye-in-Hand calibration method of Eye-on-Hand, and the fixed camera is fixed outside the mechanical arm and does not move along with the movement of the mechanical arm, so that the Eye-on-Hand calibration method of Eye-on-Hand is adopted, the camera and the fixed camera are only different in installation modes, and the calibration principle in the text is also a nine-point calibration mode. The nine-point calibration principle is that firstly, a mechanical arm is moved to enable a Mark point to exist in image visual fields of a mobile camera and a fixed camera, then a template matching or connected domain analysis method is used for finding the position of the Mark point, then the mechanical arm is moved nine times, so that the Mark point is located at different positions in an image and can be found in the image visual field every time, and nine mechanical arm coordinates and image coordinates are respectively stored. Let the coordinates of the mechanical arm be (x, y, Z), because the mechanical arm can keep the Z axis unchanged when moving, so only need to calibrate x, y. I.e. the relationship between the image coordinates and the robot coordinates is:
wherein the rotation matrix T is:
the translation matrix M is:
this gives the system of equations:
the six unknowns can be known from the equation set, and the six unknowns can be solved by at least three groups of points, however, in order to ensure the accuracy of the numerical values, more points are generally selected to solve a solution with higher accuracy by using a least square method, and the accuracy of the obtained matrix can be ensured to meet the requirements by referring to the accuracy of the mechanical arm and the accuracy of the pixels when nine groups of points are used, so that the nine groups of points are generally used for solving the rotation and translation matrix. In order to distinguish the mobile camera from the fixed camera conveniently, the coordinate transformation relation matrix of the mobile camera can be set to be Hs, and the coordinate transformation relation matrix of the fixed camera can be set to be Hx.
In step S1, the method for enabling the mobile camera to obtain the initial bit state of the memory bank through the image processing technology includes:
firstly, judging whether a memory bank exists or not by using a mobile camera on a mechanical arm, then when the memory bank exists, finding the outline of the memory bank in a specific ROI (region of interest) by using a connected domain analysis method, then dividing the ROI into a plurality of sub-regions according to the outline of the memory bank, respectively obtaining the values of x (length size) and y (width size) of the sub-regions, and judging the position of each sub-region in the ROI region according to the value of x; and then selecting the leftmost or rightmost position as the currently required memory bank position, finding the minimum external rectangle corresponding to the sub-region, moving the central point of the minimum external rectangle right to divide the minimum external rectangle into a plurality of small sub-rectangles, obtaining points with large gradient change by using a canny operator for image processing in each small sub-rectangle, and finally fitting a straight line according to the calculated points, wherein the fitted straight line is the edge contour line of the memory bank. And then, the angle of the memory bank can be calculated by a straight-line point-slope equation according to the edge contour line of the memory bank, then the central point of the minimum external rectangle of the memory bank is found, the position of the central point of the edge of the memory bank in the image can be calculated by diffusing along the central point along two sides of the memory bank in the angle direction, and finally the initial state of the memory bank can be calculated according to the position, the length and the angle of the edge contour line.
In addition, in order to improve the accuracy of the grabbing reference state of the mechanical arm, the assembling reference state of the memory bank and the inserting reference state of the memory slot, in this embodiment, before the initial state of the memory bank is obtained, pre-operation correction and determination can be performed on each reference state in advance according to actual equipment and environment.
Specifically, the method for acquiring the grabbing reference position state of the mechanical arm and the assembling reference position state of the memory bank specifically comprises the following steps:
firstly, driving a mechanical arm to drive a mobile camera to move to a preset first photographing position for photographing, storing a coordinate p6 (x 6, y6 and q 6) of the mechanical arm and a coordinate p7 (x 7, y7 and q 7) of a memory bank in an image, then manually moving the mechanical arm to drive the mobile camera to grab the memory bank, only changing a Z coordinate to a photographing height after grabbing the memory bank, and recording a mechanical arm coordinate p8 (x 8, y8 and q 8) at the moment as a reference position which needs to be grabbed by the mechanical arm. Then, the mechanical arm is moved manually to grab the memory bank and move to the shooting position of the fixed camera for shooting, and the coordinate p9 (x 9, y9 and q 9) of the memory bank is determined, wherein the coordinate is the reference position of the memory bank to be placed into the memory slot after the mechanical arm grabs the memory bank. Thus, the photographing reference potential p6 of the robot arm, the first coordinate reference potential p7 of the memory bank, the grabbing reference potential p8 of the robot arm, and the assembling reference potential p9 of the memory bank can be determined respectively. Wherein q is the attitude angle.
The method for acquiring the plug-in reference bit state of the memory slot specifically comprises the following steps:
the method comprises the steps of guiding a mobile camera to move a preset distance position above a memory slot by using a mechanical arm, slowly guiding the mechanical arm to insert a memory bar into the memory slot, lifting the mechanical arm to a photographing height of the mobile camera after the mechanical arm is inserted into the memory slot, ensuring that x and y coordinate values of the mechanical arm are unchanged at the moment, recording the mechanical arm coordinate at the moment as p1 (x 1, y1 and q 1), then moving the mechanical arm to the position where the memory slot can be clearly photographed in the field of view of the mobile camera, finding the position of the memory slot at the moment to perform image processing and recognition, calculating the coordinate of the memory slot, and respectively storing the coordinate p2 (x 2, y2 and q 2) of the mechanical arm at the moment and the coordinate p3 (x 3, y3 and q 3) of the. The point p1 is an insertion reference state when the memory bank is inserted, the point p2 is an identification reference state when the memory slot is identified, and the point p3 is a second coordinate reference state when the memory slot is identified.
In step S4, the current bit state of the memory slot is calculated as p4 (x 4, y4, q 4) by the mobile camera, then the difference between the current bit state and the second coordinate reference bit state p3 is calculated, and a more reference compensation bit state p5 (x 5, y5, q 5) is calculated according to the difference:
similarly, in step S2, when the offset amounts (xp, yp, qp) of the robot arm are calculated again, the total offset amount may be calculated according to the initial position state of the memory bank and the differences between the photographing reference position state, the first coordinate reference position state, and the capturing reference position state in sequence, and then the capturing position of the robot arm may be corrected, where the coordinate of the capturing position is p10 (x 10, y10, q 10):
in addition, in step S3, the fixed camera calculates the post-capture bit state of the memory bank as p11 (x 11, y11, q 11), and then performs difference calculation with the assembly reference bit state p9 (x 9, y9, q 9), so as to obtain the coordinates of the to-be-assembled position of the memory bank as p12 (x 12, y12, q 12):
in step S4, the compensation bit state is calculated by combining the coordinates of the to-be-mounted position of the memory bank p12 with the coordinates of the compensation bit state p5, i.e., p13 (x 13, y13, q 13) = p13 (x 12+ x5, y12+ y5, q12+ q 5).
As shown in fig. 2, fig. 2 is a system structure diagram of an embodiment of the present invention.
The embodiment also provides a machine vision-based memory alignment plugging system, which mainly comprises an initial acquisition module 1, a memory capture module 2, an attitude adjustment module 3, a slot positioning module 4 and an alignment plugging module 5.
The initial acquisition module 1 is mainly used for driving the mobile camera to move to an initial position through the mechanical arm, and enabling the mobile camera to acquire an initial state of the memory bank through an image processing technology. The memory grabbing module 2 is mainly used for calculating the offset of the mechanical arm according to the deviation value of the initial bit state and the grabbing reference bit state of the memory bank, and moving the mechanical arm to the grabbing position according to the offset to grab the memory bank. The posture adjusting module 3 is mainly used for moving the mechanical arm to a photographing position of the fixed camera, calculating a post-grabbing bit state of the memory bank through an image processing technology, and moving the mechanical arm to a position to be assembled according to a deviation value of the post-grabbing bit state and an assembling reference bit state. The slot positioning module 4 is mainly used for acquiring images of the memory slots through the mobile camera, calculating the current bit states of the memory slots through an image processing technology, and calculating the compensation bit states according to the current bit states and the plug-in reference bit states of the memory slots. The contraposition inserting module 5 is mainly used for calculating the current inserting position according to the position to be assembled and the compensation position, and moving the mechanical arm to the current inserting position to perform memory bank inserting operation.
The present embodiments also provide an apparatus, which mainly includes a memory and a processor. The memory is mainly used for storing a computer program, and the processor is mainly used for executing the computer program, so that the machine vision memory alignment-based patching method is realized in the process of executing the computer program.
In this embodiment, the device may be a server, or may also be a terminal device such as a smart phone, a tablet computer, a palmtop computer, and a portable computer.
The present embodiment also provides a storage medium, on which the foregoing computer program is stored, so that when being executed by a processor, the computer program implements the machine vision-based memory alignment patching method as described above.
In this embodiment, the storage medium may be various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
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 machine vision-based memory alignment plugging method is characterized by comprising the following steps:
driving a mobile camera to move to an initial position through a mechanical arm, and enabling the mobile camera to obtain an initial position state of a memory bank through an image processing technology;
calculating the offset of the mechanical arm according to the deviation value of the initial position state and the grabbing reference position state of the memory bank, and moving the mechanical arm to a grabbing position according to the offset to grab the memory bank;
moving the mechanical arm to a photographing position of a fixed camera, calculating a post-grabbing bit state of the memory bank through an image processing technology, and moving the mechanical arm to a position to be assembled according to a deviation value of the post-grabbing bit state and an assembly reference bit state;
acquiring images of the memory slots through the mobile camera, calculating the current bit state of the memory slots through an image processing technology, and calculating a compensation bit state according to the current bit state and the plug-in reference bit state of the memory slots;
and calculating the current plug-in mounting position state according to the position to be assembled and the compensation position state, and moving the mechanical arm to the current plug-in mounting position to perform the memory bank plug-in mounting operation.
2. The machine vision memory alignment and plugging method as claimed in claim 1, wherein before the mechanical arm drives the mobile camera to move synchronously to the initial position, the method further comprises:
and calibrating the coordinates of the photographed images of the mobile camera and the fixed camera and the position coordinates of the mechanical arm to obtain the coordinate conversion relationship between the images of the mobile camera and the mechanical arm and the coordinate conversion relationship between the images of the fixed camera and the mechanical arm.
3. The machine-vision-based memory alignment plugging method according to claim 1, wherein the step of enabling the mobile camera to obtain the initial state of the memory bank through an image processing technology specifically comprises:
and enabling the mobile camera to acquire the contour of the memory bank in a preset ROI (region of interest) through a connected domain analysis method, fitting an edge contour line of the memory bank through a straight line, and calculating the initial state of the memory bank according to the edge contour line.
4. The machine-vision-based memory alignment patching method of claim 1, further comprising, before obtaining the initial bit state of a memory bank:
and acquiring a grabbing reference position state of the mechanical arm, an assembling reference position state of the memory bank and an inserting reference position state of the memory slot.
5. The machine vision memory alignment and plugging method according to claim 4, wherein the obtaining of the grabbing reference position state of the mechanical arm specifically comprises:
driving the mobile camera to move to a photographing reference position state capable of acquiring the memory bank image through the mechanical arm;
acquiring an image of the memory bank through the mobile camera and calculating a first coordinate reference bit state of the memory bank;
and grabbing the memory bank through the mechanical arm, and vertically ascending for a preset distance to a grabbing reference position state.
6. The machine-vision-based memory alignment plugging method according to claim 5, wherein obtaining an assembly reference state of the memory bank specifically comprises:
the memory bank is held and grabbed by the mechanical arm and is moved to a photographing position of the fixed camera;
and acquiring the image of the memory bank through the fixed camera and calculating the assembly reference bit state of the memory bank.
7. The machine-vision-based memory alignment plugging method according to claim 6, wherein obtaining a plugging reference state of the memory slot specifically includes:
driving the mobile camera to move to an identification reference position state capable of acquiring the memory slot image through the mechanical arm;
acquiring an image of the memory slot through the mobile camera and calculating a second coordinate reference position state of the memory slot;
and driving the mobile camera to move to an insertion reference position state with a preset distance above the memory slot through the mechanical arm.
8. A machine vision-based memory alignment patching system, comprising:
the initial acquisition module is used for driving the mobile camera to move to an initial position through the mechanical arm and enabling the mobile camera to acquire the initial state of the memory bank through an image processing technology;
the memory grabbing module is used for calculating the offset of the mechanical arm according to the deviation value of the initial bit state and the grabbing reference bit state of the memory bank, and moving the mechanical arm to a grabbing position to grab the memory bank according to the offset;
the attitude adjusting module is used for moving the mechanical arm to a photographing position of a fixed camera, calculating a post-grabbing bit state of the memory bank through an image processing technology, and moving the mechanical arm to a position to be assembled according to a deviation value of the post-grabbing bit state and an assembling reference bit state;
the slot positioning module is used for acquiring images of the memory slots through the mobile camera, calculating the current bit state of the memory slots through an image processing technology, and calculating a compensation bit state according to the current bit state and the plug-in reference bit state of the memory slots;
and the alignment insertion module is used for calculating the current insertion position state according to the position to be assembled and the compensation position state and moving the mechanical arm to the current insertion position to perform memory bank insertion operation.
9. An apparatus, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the machine vision memory alignment-based patching method according to any one of claims 1 to 7 when executing the computer program.
10. A storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements the steps of the machine-vision-based memory alignment patching method of any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010940989.XA CN111815634A (en) | 2020-09-09 | 2020-09-09 | Machine vision-based memory alignment plug-in method, system, equipment and storage medium |
| PCT/CN2021/073258 WO2022052404A1 (en) | 2020-09-09 | 2021-01-22 | Memory alignment and insertion method and system based on machine vision, device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010940989.XA CN111815634A (en) | 2020-09-09 | 2020-09-09 | Machine vision-based memory alignment plug-in method, system, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111815634A true CN111815634A (en) | 2020-10-23 |
Family
ID=72860785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010940989.XA Pending CN111815634A (en) | 2020-09-09 | 2020-09-09 | Machine vision-based memory alignment plug-in method, system, equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111815634A (en) |
| WO (1) | WO2022052404A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113393447A (en) * | 2021-06-24 | 2021-09-14 | 四川启睿克科技有限公司 | Needle tip true position detection method and system based on deep learning |
| CN113562465A (en) * | 2021-09-26 | 2021-10-29 | 成都新西旺自动化科技有限公司 | Visual guiding method and system for sheet placement |
| WO2022052404A1 (en) * | 2020-09-09 | 2022-03-17 | 苏州浪潮智能科技有限公司 | Memory alignment and insertion method and system based on machine vision, device, and storage medium |
| CN114227187A (en) * | 2021-11-30 | 2022-03-25 | 浪潮(山东)计算机科技有限公司 | Plug-in component mounting method and system and related assembly |
| CN114725753A (en) * | 2022-02-28 | 2022-07-08 | 福建星云电子股份有限公司 | Automatic interpolation method and system based on visual guidance |
| US11867755B2 (en) | 2021-03-10 | 2024-01-09 | Changxin Memory Technologies, Inc. | Memory device test method, apparatus, and system, medium, and electronic device |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115682926B (en) * | 2022-09-07 | 2023-08-29 | 广东爱吉尔机器人科技有限公司 | One-to-many rapid hand-eye calibration method |
| CN115890654B (en) * | 2022-10-09 | 2023-08-11 | 北京微链道爱科技有限公司 | Depth camera automatic calibration algorithm based on three-dimensional feature points |
| CN116141340B (en) * | 2023-04-20 | 2023-07-14 | 中国信息通信研究院 | Double-robot flexible collaborative manipulator based on circuit board assembly |
| CN117021121B (en) * | 2023-10-09 | 2024-06-14 | 浪潮(山东)计算机科技有限公司 | Automatic memory bank installation equipment and method based on machine vision |
| CN117900810B (en) * | 2024-03-15 | 2024-07-26 | 中电鹏程智能装备有限公司 | Automatic flexible lossless insertion method and device for memory bank |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040102911A1 (en) * | 2002-11-21 | 2004-05-27 | Samsung Electronics Co., Ltd. | Hand/eye calibration method using projective invariant shape descriptor of 2-dimensional image |
| CN102692183A (en) * | 2011-03-23 | 2012-09-26 | 比比威株式会社 | Measurement method of initial positions and poses of multiple cameras |
| CN106670763A (en) * | 2017-01-10 | 2017-05-17 | 荣旗工业科技（苏州）有限公司 | Calculating method of high-precision automatic assembly machine |
| CN107443362A (en) * | 2017-09-29 | 2017-12-08 | 张浩洋 | Computer main board memory bar automatic placement device |
| CN108453727A (en) * | 2018-01-11 | 2018-08-28 | 中国人民解放军63920部队 | Mechanical arm tail end position and attitude error bearing calibration based on oval feature and system |
| CN110125926A (en) * | 2018-02-08 | 2019-08-16 | 比亚迪股份有限公司 | The workpiece of automation picks and places method and system |
| CN110374312A (en) * | 2019-07-03 | 2019-10-25 | 广东博智林机器人有限公司 | Handling system and its control method, floor tile paving system |
| CN110480615A (en) * | 2019-08-30 | 2019-11-22 | 河南省机械设计研究院有限公司 | Robot de-stacking positioning correction method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111815634A (en) * | 2020-09-09 | 2020-10-23 | 苏州浪潮智能科技有限公司 | Machine vision-based memory alignment plug-in method, system, equipment and storage medium |
-
2020
- 2020-09-09 CN CN202010940989.XA patent/CN111815634A/en active Pending
-
2021
- 2021-01-22 WO PCT/CN2021/073258 patent/WO2022052404A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040102911A1 (en) * | 2002-11-21 | 2004-05-27 | Samsung Electronics Co., Ltd. | Hand/eye calibration method using projective invariant shape descriptor of 2-dimensional image |
| CN102692183A (en) * | 2011-03-23 | 2012-09-26 | 比比威株式会社 | Measurement method of initial positions and poses of multiple cameras |
| CN106670763A (en) * | 2017-01-10 | 2017-05-17 | 荣旗工业科技（苏州）有限公司 | Calculating method of high-precision automatic assembly machine |
| CN107443362A (en) * | 2017-09-29 | 2017-12-08 | 张浩洋 | Computer main board memory bar automatic placement device |
| CN108453727A (en) * | 2018-01-11 | 2018-08-28 | 中国人民解放军63920部队 | Mechanical arm tail end position and attitude error bearing calibration based on oval feature and system |
| CN110125926A (en) * | 2018-02-08 | 2019-08-16 | 比亚迪股份有限公司 | The workpiece of automation picks and places method and system |
| CN110374312A (en) * | 2019-07-03 | 2019-10-25 | 广东博智林机器人有限公司 | Handling system and its control method, floor tile paving system |
| CN110480615A (en) * | 2019-08-30 | 2019-11-22 | 河南省机械设计研究院有限公司 | Robot de-stacking positioning correction method |
Non-Patent Citations (1)
| Title |
|---|
| 王和平: "基于机器视觉的插件机定位检测技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022052404A1 (en) * | 2020-09-09 | 2022-03-17 | 苏州浪潮智能科技有限公司 | Memory alignment and insertion method and system based on machine vision, device, and storage medium |
| US11867755B2 (en) | 2021-03-10 | 2024-01-09 | Changxin Memory Technologies, Inc. | Memory device test method, apparatus, and system, medium, and electronic device |
| CN113393447A (en) * | 2021-06-24 | 2021-09-14 | 四川启睿克科技有限公司 | Needle tip true position detection method and system based on deep learning |
| CN113393447B (en) * | 2021-06-24 | 2022-08-02 | 四川启睿克科技有限公司 | Needle tip true position detection method and system based on deep learning |
| CN113562465A (en) * | 2021-09-26 | 2021-10-29 | 成都新西旺自动化科技有限公司 | Visual guiding method and system for sheet placement |
| CN114227187A (en) * | 2021-11-30 | 2022-03-25 | 浪潮(山东)计算机科技有限公司 | Plug-in component mounting method and system and related assembly |
| CN114725753A (en) * | 2022-02-28 | 2022-07-08 | 福建星云电子股份有限公司 | Automatic interpolation method and system based on visual guidance |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022052404A1 (en) | 2022-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111815634A (en) | Machine vision-based memory alignment plug-in method, system, equipment and storage medium | |
| CN111445533B (en) | Binocular camera calibration method, device, equipment and medium | |
| US7878402B2 (en) | Decoding distorted symbols | |
| CN109788277B (en) | Method and device for compensating optical axis deviation of anti-shake movement and storage medium | |
| CN111263142B (en) | Method, device, equipment and medium for testing optical anti-shake of camera module | |
| CN111612853A (en) | Camera parameter calibration method and device | |
| CN110621150B (en) | Printed circuit board assembling method and related device | |
| CN108508680A (en) | A kind of method that camera module automatic focusing mechanism scaling board center is aligned with sensitive chip center | |
| CN109544643A (en) | A kind of camera review bearing calibration and device | |
| CN113643384B (en) | Coordinate system calibration method, automatic assembly method and device | |
| CN110705433A (en) | Bridge deformation monitoring method, device and equipment based on visual perception | |
| WO2022141324A1 (en) | Camera hardware-in-the-loop calibration and target setting method and system, and related device | |
| CN111709999A (en) | Calibration plate, camera calibration method and device, electronic equipment and camera system | |
| CN111311671B (en) | Workpiece measuring method and device, electronic equipment and storage medium | |
| CN112556994A (en) | Optical information detection method, device and equipment | |
| CN113658279B (en) | Camera internal reference and external reference estimation method, device, computer equipment and storage medium | |
| CN115965697A (en) | Projector calibration method, calibration system and device based on Samm's law | |
| CN114664721A (en) | Wafer position pre-alignment method, electronic equipment and wafer transmission system | |
| CN113910756A (en) | Compensation control method, device, equipment and medium based on screen printing alignment | |
| CN117557637A (en) | Dynamic flyswatter high-precision positioning method and device based on Mark point Mark | |
| CN113538590A (en) | Zoom camera calibration method and device, terminal equipment and storage medium | |
| CN110458951B (en) | Modeling data acquisition method and related device for power grid pole tower | |
| CN116503451A (en) | Method and system for registering and positioning inspection image targets of fixed cameras of substation | |
| CN111856895B (en) | Alignment method and device of CCD exposure machine and computer readable storage medium thereof | |
| CN115719387A (en) | 3D camera calibration method, point cloud image acquisition method and camera calibration 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201023 |