CN112365538B - Efficient target detection method of automatic reeling system - Google Patents

Efficient target detection method of automatic reeling system Download PDF

Info

Publication number
CN112365538B
CN112365538B CN202011092140.8A CN202011092140A CN112365538B CN 112365538 B CN112365538 B CN 112365538B CN 202011092140 A CN202011092140 A CN 202011092140A CN 112365538 B CN112365538 B CN 112365538B
Authority
CN
China
Prior art keywords
ellipse
point
searching
searched
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011092140.8A
Other languages
Chinese (zh)
Other versions
CN112365538A (en
Inventor
郑岗
王泽文
杨喆
徐开亮
刘刚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian University of Technology
Original Assignee
Xian University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xian University of Technology filed Critical Xian University of Technology
Priority to CN202011092140.8A priority Critical patent/CN112365538B/en
Publication of CN112365538A publication Critical patent/CN112365538A/en
Application granted granted Critical
Publication of CN112365538B publication Critical patent/CN112365538B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • G06T7/73Determining position or orientation of objects or cameras using feature-based methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/13Edge detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/136Segmentation; Edge detection involving thresholding
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10004Still image; Photographic image
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Geometry (AREA)
  • Image Analysis (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention discloses a high-efficiency target detection method of an automatic reeling system, which specifically comprises the following steps: step 1, acquiring a real-time image of a detection object through an industrial camera. Step 2, preprocessing the image obtained in the step 1; step 3, carrying out edge detection on the image obtained in the step 2 to obtain an edge image represented by a binary value; step 4, searching a target in the edge image obtained in the step 3 by utilizing a Hough transform ellipse detection method; step 5, using a dynamic ellipse searching method based on the major and minor axes, and taking the major axis of the rough ellipse searched in the step 4 as a reference to complete the searching process of the edge pixels of the ellipse from one end point to the other end point; and 6, carrying out ellipse fitting on the sample points searched out in the step 5 by adopting a least square method. The invention is based on the dynamic ellipse searching method of the major and minor axes, avoids the interference of the contour of the same type to the utmost extent, and improves the detection precision.

Description

Efficient target detection method of automatic reeling system
Technical Field
The invention belongs to the technical field of image processing and industrial detection, and relates to a high-efficiency target detection method of an automatic scrolling system.
Background
Along with the development of modern processing industry, the demand of industrial production line to automated control system is bigger and bigger to cold rolling production line decoiler is rolled up as an example, and the operator controls fixed track's hydraulic trolley through controlling the button and removes, lifts the coil of strip from the saddle, makes the coil of strip move near decoiler reel from the saddle through translation and decline to make coil of strip core and decoiler reel center align and dock again, accomplish the control of rolling up of decoiler. When aligning the steel coil, the operator often can not directly observe the state of target alignment due to the position limitation on the site, and the steel coil position needs to be repeatedly patrolled and corrected, so that the coiling step becomes very complicated, the output rate of an industrial production line is influenced, meanwhile, along with the increase of the workload of the operator, the fatigue degree is increased, the control error is very easy to occur, industrial accidents can be caused when the operation is serious, and potential safety hazards exist. The development and the demand of the society enable the research and the development and the use of an automatic coil-feeding system to be a necessary demand, the automatic coil-feeding means that the position of a steel coil is detected and positioned through a specific sensor, and after the accurate position information of the steel coil is obtained, the hydraulic trolley lifts the steel coil and automatically moves the steel coil to a target place to finish the automatic coil-feeding.
The use of the automatic coiling system greatly improves the production efficiency of the industrial production line, the currently commonly used automatic coiling system has a laser positioning type, and a laser sensor is arranged at a key point to judge whether a steel coil moves to the point or not, so that the automatic control is realized; the encoder type is used for measuring the displacement of the trolley through an encoder arranged on the trolley and indirectly calculating the position of the steel coil, and the method can ensure high precision only by ensuring that the steel coil is located at the same position on the trolley every time and the coil diameters are the same; and in the diameter measuring mode, the coil diameter of the steel coil is detected through an image sensor, so that the steel coil moves by a distance equal to the coil diameter in a descending stage, and then the steel coil is aligned with the winding drum by default. Most of the traditional methods can only realize semi-automatic control of the reeling process, full automation cannot be realized, the number of sensors in the system is large, the failure rate is high, and the difficulty of later maintenance is increased.
In order to solve the problems, an automatic coil-feeding system based on image processing is designed, the core of the automatic coil-feeding system is that an industrial camera arranged at a specific position is used for shooting the movable range area of a steel coil, and when the steel coil is automatically fed, the real-time position coordinates of the steel coil are calculated through the image processing technology, so that the whole-course positioning and tracking of the coil-feeding process are completed, and the full-automatic control of the coil-feeding process is realized. The method has strong controllability and real-time performance, and simultaneously introduces new detection disturbance such as illumination intensity, shielding and the like. When the image is processed, the problem of identifying the steel coil is converted into ellipse detection, so that main interference comes from the contour of the same type of the steel coil body plate layer, the shape and the size of the steel coil body plate layer are highly similar to those of a real target, the detection result is easy to disperse, and the detection precision is influenced.
Disclosure of Invention
The invention aims to provide an efficient target detection method of an automatic scrolling system, which is based on a dynamic ellipse search method of long and short axes, avoids the interference of profiles of the same type to the greatest extent and improves the detection precision.
The technical scheme adopted by the invention is that the high-efficiency target detection method of the automatic reeling system specifically comprises the following steps:
step 1, acquiring a real-time image of a detection object through an industrial camera, and establishing a plane rectangular coordinate system by taking the upper left corner of the image as a coordinate origin.
Step 2, preprocessing the image obtained in the step 1;
step 3, performing edge detection on the image obtained in the step 2 by adopting a Canny operator method to obtain an edge image represented by a binary value;
step 4, searching a target in the edge image obtained in the step 3 by utilizing a Hough transform ellipse detection method;
step 5, using a dynamic ellipse searching method based on the major and minor axes, and taking the major axis of the rough ellipse searched in the step 4 as a reference to complete the searching process of the edge pixels of the ellipse from one end point to the other end point;
and 6, carrying out ellipse fitting on the sample points searched out in the step 5 by adopting a least square method.
The present invention is also characterized in that,
the specific process of the step 2 is as follows: and respectively and sequentially carrying out image graying, morphological processing, histogram equalization and Gaussian filtering processing on the image.
The specific process of the step 5 is as follows:
the searching process of the ellipse major axis is as follows: respectively searching point by point in the horizontal left direction and the horizontal right direction by taking the point A as a starting point and the point C as an end point, and quitting the searching process in a certain direction when a pixel point is searched for the first time in the direction and the position of the pixel point meets the searching limit condition, so that each point on the long axis of the ellipse is searched in a traversing manner;
the search process of the ellipse short axis is as follows: and (3) with the point B as a starting point and the point D as an end point, respectively carrying out point-by-point search in the horizontal left direction and the horizontal right direction, and when a pixel point is searched for the first time in a certain direction and the position of the pixel point meets a search limiting condition, quitting the search process in the direction, and traversing and searching each point on the short axis of the ellipse by the process.
The search limiting conditions in the step 5 are as follows:
the center coordinates elc (x) of the rough ellipse can be obtained by searching the ellipse in step 4 e ,y e ) The major axis length h, the minor axis w and the inclination angle theta, and calculating the focal coordinates of the ellipse in the plane according to the parameters, wherein when theta is in the range of 0 and 90, the focal coordinates of the ellipse are shown as the formula (1), and in the formula, two focuses of the ellipse are C 1 (x c1 ,y c1 ) And C 2 (x c2 ,y c2 ) In which
Figure BDA0002722476900000041
Figure BDA0002722476900000042
When theta belongs to [90,180), the focal coordinates of the ellipse are as shown in formula (2), wherein two focuses of the ellipse are C 1 (x c1 ,y c1 ) And C 2 (x c2 ,y c2 ) Wherein
Figure BDA0002722476900000043
Figure BDA0002722476900000044
If the pixel point searched in step 5 is P (x) p ,y p ),C 1 And C 2 The two focuses of the ellipse are determined as the real target pixel point when the ellipse satisfies the following formula (3):
Figure BDA0002722476900000045
in the formula, | PC 1 I and I PC 2 I respectively represent a point P to two foci C 1 And C 2 T is a threshold value.
The method has the advantages that the efficient target detection method of the automatic coil-feeding system converts the identification problem of the steel coil into ellipse detection, the flow chart of the method is shown in figure 1, firstly, a real-time image is obtained through an industrial camera, then, the image is preprocessed, then, edge detection is carried out on the image to obtain a binary edge image, contour pixel points of a target ellipse are searched in the edge image, high-precision fitting is carried out after the contour pixel points are sorted, position coordinates and size parameters of the ellipse are obtained, and the method is equivalent to the completion of positioning of the steel coil. The method provided by the invention avoids the interference of the contour of the same type to a great extent and improves the detection precision.
Drawings
FIG. 1 is a flow chart of a method for efficient target detection for an automatic rollup system of the present invention;
FIG. 2 is a schematic diagram of a source image and a coordinate system setup in the efficient target detection method of the automatic scrolling system according to the present invention;
FIG. 3 is a schematic diagram of image preprocessing in an efficient target detection method of an automatic scrolling system according to the present invention;
FIG. 4 is a schematic diagram of edge detection in an efficient target detection method of an automatic scrolling system according to the invention;
FIG. 5 is a schematic diagram of Hough transform ellipse search in an efficient target detection method of an automatic scrolling system according to the present invention;
FIG. 6 is a schematic diagram of a dynamic ellipse searching method based on major and minor axes in the efficient target detection method of the automatic scrolling system according to the present invention;
FIG. 7 is a schematic diagram illustrating a relationship between positions of a sample point and an ellipse in the efficient target detection method of the automatic scrolling system according to the present invention;
FIG. 8 is a diagram illustrating the detection results of the efficient target detection method of the automatic scrolling system according to the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The invention provides an efficient target detection method of an automatic coil-feeding system, which converts the identification problem of a steel coil into ellipse detection, and the flow chart of the method is shown in figure 1.
The invention relates to a high-efficiency target detection method of an automatic reeling system, which comprises the following specific processes:
step 1, acquiring a real-time image of a detection object through an industrial camera, and converting a steel coil detection problem into ellipse detection by taking a steel coil center circle as a target and actually forming an ellipse in two-dimensional imaging. A rectangular plane coordinate system is established by taking the upper left corner of the image as the origin of coordinates, and a schematic diagram of the rectangular plane coordinate system is shown in FIG. 2.
And 2, preprocessing the image acquired in the step 1, wherein the preprocessing comprises the steps of image graying, morphological processing, histogram equalization and Gaussian filtering, and the image preprocessing is performed to enhance the image effect and facilitate detection, and the image preprocessing schematic diagram is shown in FIG. 3.
And 3, performing edge detection on the image obtained in the step 2 by adopting a Canny operator method to obtain an edge image represented by a binary value, as shown in fig. 4.
And 4, searching a target in the edge image obtained in the step 3 by using a Hough transform ellipse detection method, wherein the detection result of the method has a certain error due to certain randomness of Hough transform, as shown in FIG. 5.
Step 5, using the dynamic ellipse searching method based on the major and minor axes, and using the rough ellipse major axis searched in step 4 as a reference, completing the searching process of the ellipse edge pixels from one end point to the other end point, wherein the specific searching process is that a major axis group is shown in fig. 6(a), using point a as a starting point and point C as an end point, respectively performing point-by-point searching in two directions of horizontal left and horizontal right, when a pixel point is searched for the first time in a certain direction and the position of the pixel point meets the searching limit condition, exiting the searching process in the direction, and traversing and searching each point on the major axis in the step; as shown in fig. 6(B), the short axis group searches and traverses the points on the short axis according to the same search pattern as the long axis, with point B as the starting point and point D as the ending point. The search mode can effectively filter the interference points outside the true elliptical contour, but is insensitive to the interference points inside the ellipse, so that the limit condition of the search is set, the interference pixel points inside the ellipse are also filtered, and the setting method of the limit condition is as follows:
the center coordinates elc (x) of the rough ellipse can be obtained by searching the ellipse in step 4 e ,y e ) The focal coordinates of the ellipse in the plane are calculated according to the parameters, wherein when theta belongs to [0,90 ], the focal coordinates of the ellipse are shown as formula (1), wherein two focuses of the ellipse are C 1 (x c1 ,y c1 ) And C 2 (x c2 ,y c2 ) Wherein
Figure BDA0002722476900000071
Figure BDA0002722476900000072
When theta belongs to [90,180), the focal coordinates of the ellipse are as shown in formula (2), wherein two focuses of the ellipse are C 1 (x c1 ,y c1 ) And C 2 (x c2 ,y c2 ) Wherein
Figure BDA0002722476900000073
Figure BDA0002722476900000074
If the pixel point searched in step 5 is P (x) p ,y p ) The positional relationship between the pixel point and the ellipse is shown in FIG. 7, C 1 And C 2 The two focuses of the ellipse are determined as the real target pixel points when the two focuses need to satisfy the formula (3).
Figure BDA0002722476900000075
In the formula, | PC 1 I and I PC 2 I respectively represent a point P to two foci C 1 And C 2 T is a threshold value and can be adjusted according to actual conditions.
And 6, carrying out ellipse fitting on the sample points searched in the step 5 by adopting a least square method to obtain position coordinates and shape parameters of an ellipse, refreshing position records in a system, and circularly executing a program when the program detects and positions the moving steel coil, wherein the ellipse information detected in the step is used as the latest position information to replace the result searched by the Hough transform method in the step 4, so that the tracking and positioning of the dynamic target are realized, and a schematic diagram of the result detected by the method is shown in fig. 8.

Claims (1)

1. An efficient target detection method of an automatic reeling system is characterized in that: the method specifically comprises the following steps:
step 1, acquiring a real-time image of a detection object through an industrial camera, and establishing a plane rectangular coordinate system by taking the upper left corner of the image as a coordinate origin;
step 2, preprocessing the image obtained in the step 1;
the specific process of the step 2 is as follows: carrying out image graying, morphological processing, histogram equalization and Gaussian filtering processing on the image respectively in sequence;
step 3, performing edge detection on the image obtained in the step 2 by adopting a Canny operator method to obtain an edge image represented by a binary value;
step 4, searching a target in the edge image obtained in the step 3 by utilizing a Hough transform ellipse detection method;
step 5, using a dynamic ellipse searching method based on the major and minor axes, and taking the major axis of the rough ellipse searched in the step 4 as a reference to complete the searching process of the edge pixels of the ellipse from one end point to the other end point;
the specific process of the step 5 is as follows:
the searching process of the ellipse major axis is as follows: respectively searching point by point in the horizontal left direction and the horizontal right direction by taking the point A as a starting point and the point C as an end point, and quitting the searching process in a certain direction when a pixel point is searched for the first time in the direction and the position of the pixel point meets the searching limit condition, so that each point on the long axis of the ellipse is searched in a traversing manner;
the search process of the ellipse short axis is as follows: respectively searching the points one by one in the horizontal left direction and the horizontal right direction by taking the point B as a starting point and the point D as an end point, and quitting the searching process in a certain direction when a pixel point is searched for the first time in the direction and the position of the pixel point meets the searching limit condition, so that each point on the minor axis of the ellipse is searched in a traversing manner;
the search limiting conditions in the step 5 are as follows:
the center coordinates elc (x) of the rough ellipse can be obtained by searching the ellipse in step 4 e ,y e ) The major axis length h, the minor axis w and the inclination angle theta, and calculating the focal coordinates of the ellipse in the plane according to the parameters, wherein when theta is in the range of 0 and 90, the focal coordinates of the ellipse are shown as the formula (1), and in the formula, two focuses of the ellipse are C 1 (x c1 ,y c1 ) And C 2 (x c2 ,y c2 ) Wherein
Figure FDA0003512734180000021
Figure FDA0003512734180000022
When theta belongs to [90,180), the focal coordinates of the ellipse are as shown in formula (2), wherein two focuses of the ellipse are C 1 (x c1 ,y c1 ) And C 2 (x c2 ,y c2 ) Wherein
Figure FDA0003512734180000023
Figure FDA0003512734180000024
If the pixel point searched in the step 5 is P (x) p ,y p ),C 1 And C 2 The two focuses of the ellipse are determined as the real target pixel point when the ellipse satisfies the following formula (3):
Figure FDA0003512734180000025
in the formula, | PC 1 I and I PC 2 I respectively represent a point P to two foci C 1 And C 2 T is a threshold value;
and 6, carrying out ellipse fitting on the sample points searched out in the step 5 by adopting a least square method.
CN202011092140.8A 2020-10-13 2020-10-13 Efficient target detection method of automatic reeling system Active CN112365538B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011092140.8A CN112365538B (en) 2020-10-13 2020-10-13 Efficient target detection method of automatic reeling system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011092140.8A CN112365538B (en) 2020-10-13 2020-10-13 Efficient target detection method of automatic reeling system

Publications (2)

Publication Number Publication Date
CN112365538A CN112365538A (en) 2021-02-12
CN112365538B true CN112365538B (en) 2022-08-16

Family

ID=74507908

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011092140.8A Active CN112365538B (en) 2020-10-13 2020-10-13 Efficient target detection method of automatic reeling system

Country Status (1)

Country Link
CN (1) CN112365538B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113269043B (en) * 2021-04-27 2023-08-18 辽宁科技大学 Real-time tracking and identifying method and device for coil loosening of steel coil
CN113284117B (en) * 2021-05-28 2022-10-18 中冶赛迪信息技术(重庆)有限公司 Steel coil unwinding identification method, system, medium and terminal

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013003890A (en) * 2011-06-17 2013-01-07 Canon Inc Image processing system, image processing method and program
CN111178173A (en) * 2019-12-14 2020-05-19 杭州电子科技大学 Target colony growth characteristic identification method

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB201300198D0 (en) * 2013-01-07 2013-02-20 Isis Innovation Methods and apparatus for image processing
CN103150730A (en) * 2013-03-07 2013-06-12 南京航空航天大学 Round small target accurate detection method based on image
CN106530349A (en) * 2016-10-25 2017-03-22 成都工业学院 Dynamic positioning method and device based on ellipse center
CN110070537B (en) * 2019-04-25 2021-10-15 清华大学 Intelligent identification method and device for granularity and sphericity of static image particles
CN111308987B (en) * 2020-02-21 2022-12-02 西安理工大学 Automatic uncoiling control system of uncoiler based on image processing and detection method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013003890A (en) * 2011-06-17 2013-01-07 Canon Inc Image processing system, image processing method and program
CN111178173A (en) * 2019-12-14 2020-05-19 杭州电子科技大学 Target colony growth characteristic identification method

Also Published As

Publication number Publication date
CN112365538A (en) 2021-02-12

Similar Documents

Publication Publication Date Title
CN112365538B (en) Efficient target detection method of automatic reeling system
CN111308987B (en) Automatic uncoiling control system of uncoiler based on image processing and detection method
CN110501342B (en) Cheese yarn rod positioning visual detection method
CN106182004A (en) The method of the industrial robot automatic pin hole assembling that view-based access control model guides
CN110293559B (en) Installation method for automatically identifying, positioning and aligning
CN107014291B (en) A kind of vision positioning method of material precision transfer platform
CN104923593A (en) Vision-based positioning method for top layer bending plate
CN110514664B (en) Cheese yarn rod positioning and detecting robot and method
CN108106554B (en) Machine vision-based large ring outer diameter detection system and method
CN109785319A (en) A kind of coding character machining system, device and detection method based on image procossing
CN106908444A (en) A kind of taper roll bearing end face identifying system and method based on image procossing
CN109540918B (en) Hot-rolled coil edge defect detection device and method
CN111754422A (en) Visual edge inspection method based on EDLines and LSM
CN110728657A (en) Annular bearing outer surface defect detection method based on deep learning
CN109544513A (en) A kind of steel pipe end surface defect extraction knowledge method for distinguishing
CN111539951B (en) Visual detection method for outline size of ceramic grinding wheel head
CN113432585A (en) Non-contact hub position accurate measurement method based on machine vision technology
CN109741311B (en) Aluminum alloy fusion welding back face fusion width detection method with false edge
CN109443220B (en) Coil length measuring method of winding machine based on stroke measuring sensor and machine vision
CN101398291B (en) Band steel tracking imaging vision detection method
CN116000701A (en) Tool detection device and method capable of being integrated on tool magazine
CN115446125A (en) Automatic steel rotating control method for medium plate based on machine vision
CN114486913A (en) Method for detecting geometric characteristics of edge of steel coil
CN206788048U (en) A kind of taper roll bearing end face identifying system based on image procossing
CN113406920A (en) Box positioning control system and method based on machine vision

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