CN111968104A - Machine vision-based steel coil abnormity identification method, system, equipment and medium - Google Patents

Machine vision-based steel coil abnormity identification method, system, equipment and medium Download PDF

Info

Publication number
CN111968104A
CN111968104A CN202010878551.3A CN202010878551A CN111968104A CN 111968104 A CN111968104 A CN 111968104A CN 202010878551 A CN202010878551 A CN 202010878551A CN 111968104 A CN111968104 A CN 111968104A
Authority
CN
China
Prior art keywords
steel coil
target
target steel
ymin
ymax
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010878551.3A
Other languages
Chinese (zh)
Other versions
CN111968104B (en
Inventor
庞殊杨
刘雨佳
冉星明
刘睿
张超杰
贾鸿盛
毛尚伟
唐安琪
杜一杰
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.)
CISDI Chongqing Information Technology Co Ltd
Original Assignee
CISDI Chongqing Information Technology Co Ltd
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 CISDI Chongqing Information Technology Co Ltd filed Critical CISDI Chongqing Information Technology Co Ltd
Priority to CN202010878551.3A priority Critical patent/CN111968104B/en
Publication of CN111968104A publication Critical patent/CN111968104A/en
Application granted granted Critical
Publication of CN111968104B publication Critical patent/CN111968104B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • 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
    • Y—GENERAL 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a machine vision-based steel coil abnormity identification method, system, equipment and medium, wherein the method comprises the following steps: acquiring associated characteristic information of a target steel coil, wherein the associated characteristic information comprises position information of the target steel coil; comparing the position information with a preset region of interest, and judging whether the target steel coil is in a designated region; and if the target steel coil is in the designated area, identifying the corresponding serial number and the width of the target steel coil, and determining the target steel coil with abnormal width and the corresponding serial number. Marking the steel coil picture of the target steel coil, determining the steel coil characteristics in the picture and recording corresponding position information, extracting and learning the steel coil characteristics, acquiring an identification model, identifying the steel coil through the identification model, identifying whether the target steel coil is in a specified area, detecting whether the width of the target steel coil is abnormal and identifying the corresponding serial number of the target steel coil, realizing the identification and monitoring of the steel coil abnormality, and avoiding causing potential safety risks.

Description

Machine vision-based steel coil abnormity identification method, system, equipment and medium
Technical Field
The invention relates to the technical field of detection, in particular to a method, a system, equipment and a medium for identifying steel coil abnormity based on machine vision.
Background
In the production of steel products, steel coils are an important product for convenient storage and transportation. In the process of finishing and packing the steel coil, the situations that the width of the steel coil exceeds the standard and the coil shape is abnormal after the steel coil is packed are easy to occur. Influenced by the field working condition, the steel coil is not convenient to identify and monitor abnormally, and potential safety risks are further caused.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide a method, a system, a device and a medium for identifying abnormal steel coils based on machine vision, which are used to solve the problem in the prior art that the abnormal steel coils are not easy to identify and monitor.
In order to achieve the above and other related objects, the present invention provides a method for identifying an abnormal steel coil based on machine vision, including:
acquiring associated characteristic information of a target steel coil, wherein the associated characteristic information comprises position information of the target steel coil;
comparing the position information with a preset region of interest, and judging whether the target steel coil is in a designated region;
and if the target steel coil is in the designated area, identifying the corresponding serial number and the width of the target steel coil, and determining the target steel coil with abnormal width and the corresponding serial number.
Optionally, the step of obtaining the associated characteristic information of the target steel coil includes: and identifying a target steel coil and a corresponding external rectangular frame in the steel coil picture through a target detection convolutional neural network, and determining the associated characteristic information through the external rectangular frame.
Optionally, the associated feature information includes:
filename,width,height,depth,xmin,ymin,xmax,ymax，class
the filename is the name of the steel coil picture, width, height, depth is length, width and depth information corresponding to the steel coil picture, xmin and ymin are x and y coordinate values of the upper left corner of the external rectangular frame in the steel coil picture respectively, xmax and ymax are x and y coordinate values of the lower right corner of the external rectangular frame in the steel coil picture respectively, and class is a target category.
Optionally, the step of judging whether the target steel coil is in the designated area includes:
judging whether the central line of the target steel coil falls into a preset region of interest, if so, determining that the target steel coil is in a specified region, wherein the mathematical expression of judging whether the central line of the target steel coil falls into the preset region of interest is as follows:
yminR<liney<ymaxR
liney＝(ymin+ymax)/2
[yminR,xminR,ymaxR,xmaxR]
wherein, yminR、xminR、ymaxR、xmaxRFor the preset coordinate value of the region of interest, ymin is the y coordinate value of the upper left corner of the external rectangular frame in the steel coil picture, and ymax is the y coordinate value of the external rectangular frame in the steel coil pictureAnd liney is the coordinate of the center line of the target steel coil.
Optionally, the step of identifying the corresponding serial number of the target steel coil includes:
identifying the number of the target steel coil in the designated area, sequentially comparing, recording two digits as a digit a and a digit b, and respectively recording the position information of the digit a and the digit b as follows:
[ymina,xmina,ymaxa,xmaxa]
[yminb,xminb,ymaxb,xmaxb]
when the position information of the number a and the number b meets the merging mapping, the corresponding sequence of the target steel coil is determined by the number
Number, the mathematical expression of the merged mapping is:
|xmaxa-xminb|<threshold1
|ymina-yminb|<threshold2
|ymaxa-ymaxb|<threshold3
wherein, ymina、xmina、ymaxa、xmaxaCoordinates of the number a, yminb、xminb、ymaxb、xmaxbAs coordinates of the number b, threshold1, threshold2, and threshold3 are the first threshold, the second threshold, and the third threshold, respectively.
Optionally, the step of identifying the width abnormality of the target steel coil includes:
|xmax-xmin|>threshold4
wherein xmin is an x coordinate value of the upper left corner of the external rectangular frame in the steel coil picture, xmax is an x coordinate value of the lower right corner of the external rectangular frame in the steel coil picture, | xmax-xmin | is the width of the target steel coil, and threshold4 is the width threshold of the steel coil.
Optionally, the target detection convolutional neural network includes an SSD convolutional neural network, a Yolo convolutional neural network, or a fast-RCNN convolutional neural network.
A steel coil abnormity identification system based on machine vision comprises:
the acquisition module is used for acquiring the associated characteristic information of the target steel coil, wherein the associated characteristic information comprises the position information of the target steel coil;
the comparison module is used for comparing the position information of the target steel coil with a preset region of interest and judging whether the target steel coil is in a designated region or not;
and the judging module is used for identifying the corresponding serial number and the width of the target steel coil and determining the target steel coil with abnormal width and the corresponding serial number.
An apparatus, comprising:
one or more processors; and
one or more machine-readable media having instructions stored thereon that, when executed by the one or more processors, cause the apparatus to perform one or more of the methods described.
One or more machine-readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform one or more of the methods described.
As described above, the method, system, device and medium for identifying abnormal steel coils based on machine vision of the present invention have the following beneficial effects:
marking the steel coil picture of the target steel coil, determining the steel coil characteristics in the picture and recording corresponding position information, and dividing the data set of the steel coil picture according to a training set, a test set and a verification set, extracting and learning the steel coil characteristics, acquiring an identification model, identifying the steel coil under an industrial production scene through the identification model, identifying whether the target steel coil is in a designated area, detecting whether the width of the target steel coil is abnormal and identifying the corresponding sequence number of the target steel coil, realizing the identification and monitoring of the steel coil abnormality, and avoiding causing potential safety risks.
Drawings
Fig. 1 is a schematic diagram illustrating a method for identifying an abnormal steel coil based on machine vision according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a steel coil abnormality identification system based on machine vision according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention.
It should be noted that the drawings provided in the present embodiment are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated. The structures, proportions, sizes, and other dimensions shown in the drawings and described in the specification are for understanding and reading the present disclosure, and are not intended to limit the scope of the present disclosure, which is defined in the claims, and are not essential to the art, and any structural modifications, changes in proportions, or adjustments in size, which do not affect the efficacy and attainment of the same are intended to fall within the scope of the present disclosure. In addition, the terms "upper", "lower", "left", "right", "middle" and "one" used in the present specification are for clarity of description, and are not intended to limit the scope of the present invention, and the relative relationship between the terms and the terms is not to be construed as a scope of the present invention.
Referring to fig. 1, the present invention provides a method for identifying an abnormal steel coil based on machine vision, including:
s1: acquiring associated characteristic information of a target steel coil, wherein the associated characteristic information comprises position information of the target steel coil;
s2: comparing the position information with a preset region of interest, and judging whether the target steel coil is in a designated region;
s3: and if the target steel coil is in the designated area, identifying the corresponding serial number and the width of the target steel coil, and determining the target steel coil with abnormal width and the corresponding serial number. For example, a steel coil picture of a target steel coil is intercepted through an industrial scene camera to be marked, steel coil characteristics in the picture are determined, corresponding position information is recorded, a data set of the steel coil picture is divided according to a training set, a test set and a verification set, the steel coil characteristics are extracted and learned until an optimal identification model is obtained, the steel coil is identified under an industrial production scene through the identification model, whether the target steel coil is in a designated area or not is identified, whether the width of the target steel coil is abnormal or not is detected, and the corresponding serial number of the target steel coil is identified, the identification and the monitoring of the abnormality of the steel coil are realized, and potential safety risks are avoided.
In some implementations, the step of obtaining the associated characteristic information of the target steel coil includes: identifying a target steel coil and a corresponding external rectangular frame in a steel coil picture through a target detection convolutional neural network, and determining associated characteristic information through the external rectangular frame, wherein the target detection convolutional neural network comprises an SSD convolutional neural network, a Yolo convolutional neural network or a Faster-RCNN convolutional neural network, and the associated characteristic information obtained through the target detection convolutional neural network comprises:
filename,width,height,depth,xmin,ymin,xmax,ymax,class
the filename is the name of the steel coil picture, width, height, depth is length, width and depth information corresponding to the steel coil picture, xmin and ymin are x and y coordinate values of the upper left corner of the external rectangular frame in the steel coil picture respectively, xmax and ymax are x and y coordinate values of the lower right corner of the external rectangular frame in the steel coil picture respectively, and class is a target category.
Calling an identification model to acquire position information, target category and confidence coefficient of steel coil characteristics in a steel coil image, setting a specified confidence coefficient threshold, and when the confidence coefficient of a detected target is greater than the threshold, determining that the target steel coil is detected in the steel coil image, returning the position information, the target category and the confidence coefficient of the target steel coil, wherein the format and the content of the position information are as follows:
[xmin,ymin,xmax,ymax]
wherein xmin and ymin are horizontal and vertical coordinate values of the upper left corner of the circumscribed rectangle frame in the steel coil picture respectively; xmax and ymax are respectively the horizontal and vertical coordinate values of the external rectangular frame at the lower right corner in the steel coil picture.
In some implementations, the step of determining whether the target steel coil is in the designated area includes:
judging whether the central line of the target steel coil falls into a preset region of interest (ROI), if so, determining that the target steel coil is in a designated region, wherein the mathematical expression of judging whether the central line of the target steel coil falls into the preset ROI is as follows:
yminR<liney<ymaxR
liney＝(ymin+ymax)/2
[yminR,xminR,ymaxR,xmaxR]
wherein, yminR、xminR、ymaxR、xmaxRThe coordinate value of the preset region of interest is ymin, the y coordinate value of the upper left corner of the external rectangular frame in the steel coil picture is ymax, the y coordinate value of the lower right corner of the external rectangular frame in the steel coil picture is ymax, and liney is the coordinate of the central line of the target steel coil;
when the mathematical expression is not satisfied, it can be determined that the target steel coil is not in the designated area.
In some implementations, the step of identifying the corresponding serial number of the target steel coil includes:
identifying the number of the target steel coil in the designated area, sequentially comparing, recording two digits as a digit a and a digit b, and respectively recording the position information of the digit a and the digit b as follows:
[ymina,xmina,ymaxa,xmaxa]
[yminb,xminb,ymaxb,xmaxb]
when the position information of the number a and the number b meets the merging mapping, the corresponding sequence of the target steel coil is determined by the number
Number, the mathematical expression of the merged mapping is:
|xmaxa-xminb|<threshold1
|ymina-yminb|<threshold2
|ymaxa-ymaxb|<threshold3
wherein, ymina、xmina、ymaxa、xmaxaCoordinates of the number a, yminb、xminb、ymaxb、xmaxbThe method is characterized in that the coordinates are coordinates of a number b, and a threshold1, a threshold2 and a threshold3 are respectively a first threshold, a second threshold and a third threshold, namely when two numbers simultaneously meet the condition that the left-right distance is smaller than a threshold1, and the upper boundary distance and the lower boundary distance are respectively smaller than a threshold2 and a threshold3, the two numbers are determined to be different digital objects in the same group of serial numbers, after the numbers a and b meet a combination rule, information of the numbers a and b is combined, the number category is updated to be ab, the number ab is used as an object, the process is repeated for the rest numbers, and the corresponding between the numbers and a steel coil is completed.
In some implementations, the step of identifying the width abnormality of the target steel coil includes:
|xmax-xmin|>threshold4
the method comprises the steps that xmin is the coordinate value of the upper left corner x of an external rectangular frame in a steel coil picture, xmax is the coordinate value of the lower right corner x of the external rectangular frame in the steel coil picture, threshold4 is the width threshold of a steel coil, and when the width | xmax-xmin | of a target steel coil is larger than the width threshold value threshold4 of the steel coil, the width of the steel coil is judged to be abnormal, and an identification result is alarmed and processed.
Referring to fig. 2, a steel coil abnormality recognition system based on machine vision includes:
the acquisition module 10 is configured to acquire associated feature information of a target steel coil, where the associated feature information includes position information of the target steel coil;
the comparison module 20 is configured to compare the position information of the target steel coil with a preset region of interest, and determine whether the target steel coil is in a designated region;
and the judging module 30 is configured to identify the corresponding serial number and the width of the target steel coil, and determine the target steel coil with abnormal width and the corresponding serial number. The coil of strip picture through industry scene camera intercepting target coil of strip is marked, confirm coil of strip characteristic and the corresponding positional information of record in the picture, and with the data set of coil of strip picture according to the training set, the test set, verify the set and divide, draw the study to coil of strip characteristic, until obtaining preferred identification model, coil of strip discernment under the industrial production scene through identification model, whether discernment target coil of strip is in the specified area, whether the width of detection target coil of strip is unusual and the corresponding sequence number of discernment target coil of strip, realize the discernment and the control unusual to coil of strip, avoid causing potential safety risk.
Optionally, the step of obtaining the associated characteristic information of the target steel coil includes: and identifying a target steel coil and a corresponding external rectangular frame in the steel coil picture through a target detection convolutional neural network, and determining the associated characteristic information through the external rectangular frame.
Optionally, the associated feature information includes:
filename,width,height,depth,xmin,ymin,xmax,ymax,class
the filename is the name of the steel coil picture, width, height, depth is length, width and depth information corresponding to the steel coil picture, xmin and ymin are x and y coordinate values of the upper left corner of the external rectangular frame in the steel coil picture respectively, xmax and ymax are x and y coordinate values of the lower right corner of the external rectangular frame in the steel coil picture respectively, and class is a target category.
Optionally, the step of judging whether the target steel coil is in the designated area includes:
judging whether the central line of the target steel coil falls into a preset region of interest, if so, determining that the target steel coil is in a specified region, wherein the mathematical expression of judging whether the central line of the target steel coil falls into the preset region of interest is as follows:
yminR<liney<ymaxR
liney＝(ymin+ymax)/2
[yminR,xminR,ymaxR,xmaxR]
wherein, yminR、xminR、ymaxR、xmaxRAnd the ymin is a preset coordinate value of the region of interest, the ymin is a y coordinate value of the upper left corner of the external rectangular frame in the steel coil picture, the ymax is a y coordinate value of the lower right corner of the external rectangular frame in the steel coil picture, and the liney is a coordinate of the central line of the target steel coil.
Optionally, the step of identifying the corresponding serial number of the target steel coil includes:
identifying the number of the target steel coil in the designated area, sequentially comparing, recording two digits as a digit a and a digit b, and respectively recording the position information of the digit a and the digit b as follows:
[ymina,xmina,ymaxa,xmaxa]
[yminb,xminb,ymaxb,xmaxb]
when the position information of the number a and the number b meets the merging mapping, the corresponding serial number of the target steel coil is determined through the number, and the mathematical expression of the merging mapping is as follows:
|xmaxa-xminb|<threshold1
|ymina-yminb|<threshold2
|ymaxa-ymaxb|<threshold3
wherein, ymina、xmina、ymaxa、xmaxaCoordinates of the number a, yminb、xminb、ymaxb、xmaxbAs coordinates of the number b, threshold1, threshold2, and threshold3 are the first threshold, the second threshold, and the third threshold, respectively.
Optionally, the step of identifying the width abnormality of the target steel coil includes:
|xmax-xmin|>threshold4
wherein xmin is an x coordinate value of the upper left corner of the external rectangular frame in the steel coil picture, xmax is an x coordinate value of the lower right corner of the external rectangular frame in the steel coil picture, | xmax-xmin | is the width of the target steel coil, and threshold4 is the width threshold of the steel coil.
Optionally, the target detection convolutional neural network includes an SSD convolutional neural network, a Yolo convolutional neural network, or a fast-RCNN convolutional neural network.
An embodiment of the present invention provides an apparatus, including: one or more processors; and one or more machine readable media having instructions stored thereon that, when executed by the one or more processors, cause the apparatus to perform one or more of the methods described. The invention is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
Embodiments of the invention also provide one or more machine-readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform one or more of the methods described herein. The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.

Claims (10)

1. A steel coil abnormity identification method based on machine vision is characterized by comprising the following steps:
acquiring associated characteristic information of a target steel coil, wherein the associated characteristic information comprises position information of the target steel coil;
comparing the position information with a preset region of interest, and judging whether the target steel coil is in a designated region;
and if the target steel coil is in the designated area, identifying the corresponding serial number and the width of the target steel coil, and determining the target steel coil with abnormal width and the corresponding serial number.
2. The machine vision-based steel coil abnormality recognition method according to claim 1, wherein the step of obtaining the associated characteristic information of the target steel coil includes: and identifying a target steel coil and a corresponding external rectangular frame in the steel coil picture through a target detection convolutional neural network, and determining the associated characteristic information through the external rectangular frame.
3. The machine vision-based steel coil abnormality identification method according to claim 1 or 2, wherein the associated feature information includes:
filename,width,height,depth,xmin,ymin,xmax,ymax,class
the filename is the name of the steel coil picture, width, height, depth is length, width and depth information corresponding to the steel coil picture, xmin and ymin are x and y coordinate values of the upper left corner of the external rectangular frame in the steel coil picture respectively, xmax and ymax are x and y coordinate values of the lower right corner of the external rectangular frame in the steel coil picture respectively, and class is a target category.
4. The machine vision-based steel coil abnormality recognition method according to claim 1, wherein the step of judging whether the target steel coil is in a designated area includes:
judging whether the central line of the target steel coil falls into a preset region of interest, if so, determining that the target steel coil is in a specified region, wherein the mathematical expression of judging whether the central line of the target steel coil falls into the preset region of interest is as follows:
yminR<liney<ymaxR
liney＝(ymin+ymax)/2
[yminR,xminR,ymaxR,xmaxR]
wherein, yminR、xminR、ymaxR、xmaxRAnd the ymin is a preset coordinate value of the region of interest, the ymin is a y coordinate value of the upper left corner of the external rectangular frame in the steel coil picture, the ymax is a y coordinate value of the lower right corner of the external rectangular frame in the steel coil picture, and the liney is a coordinate of the central line of the target steel coil.
5. The machine vision-based steel coil abnormality identification method according to claim 1, wherein the step of identifying the corresponding serial number of the target steel coil includes:
identifying the number of the target steel coil in the designated area, sequentially comparing, recording two digits as a digit a and a digit b, and respectively recording the position information of the digit a and the digit b as follows:
[ymina,xmina,ymaxa,xmaxa]
[yminb,xminb,ymaxb,xmaxb]
when the position information of the number a and the number b meets the merging mapping, the corresponding serial number of the target steel coil is determined through the number, and the mathematical expression of the merging mapping is as follows:
|xmaxa-xminb|<threshold1
|ymina-yminb|<threshold2
|ymaxa-ymaxb|<threshold3
wherein, ymina、xmina、ymaxa、xmaxaCoordinates of the number a, yminb、xminb、ymaxb、xmaxbAs coordinates of the number b, threshold1, threshold2, and threshold3 are the first threshold, the second threshold, and the third threshold, respectively.
6. The machine vision-based steel coil abnormality identification method according to claim 1 or 2, wherein the step of identifying the width abnormality of the target steel coil includes:
|xmax-xmin|>threshold4
wherein xmin is an x coordinate value of the upper left corner of the external rectangular frame in the steel coil picture, xmax is an x coordinate value of the lower right corner of the external rectangular frame in the steel coil picture, | xmax-xmin | is the width of the target steel coil, and threshold4 is the width threshold of the steel coil.
7. The machine vision-based steel coil abnormality identification method according to claim 2, wherein the target detection convolutional neural network comprises an SSD convolutional neural network, a Yolo convolutional neural network, or a fast-RCNN convolutional neural network.
8. The utility model provides a coil of strip abnormal recognition system based on machine vision which characterized in that includes:
the acquisition module is used for acquiring the associated characteristic information of the target steel coil, wherein the associated characteristic information comprises the position information of the target steel coil;
the comparison module is used for comparing the position information of the target steel coil with a preset region of interest and judging whether the target steel coil is in a designated region or not;
and the judging module is used for identifying the corresponding serial number and the width of the target steel coil and determining the target steel coil with abnormal width and the corresponding serial number.
9. An apparatus, comprising:
one or more processors; and
one or more machine-readable media having instructions stored thereon that, when executed by the one or more processors, cause the apparatus to perform the method recited by one or more of claims 1-7.
10. One or more machine-readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform the method recited by one or more of claims 1-7.
CN202010878551.3A 2020-08-27 2020-08-27 Machine vision-based steel coil abnormity identification method, system, equipment and medium Active CN111968104B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010878551.3A CN111968104B (en) 2020-08-27 2020-08-27 Machine vision-based steel coil abnormity identification method, system, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010878551.3A CN111968104B (en) 2020-08-27 2020-08-27 Machine vision-based steel coil abnormity identification method, system, equipment and medium

Publications (2)

Publication Number Publication Date
CN111968104A true CN111968104A (en) 2020-11-20
CN111968104B CN111968104B (en) 2023-04-07

Family

ID=73399359

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010878551.3A Active CN111968104B (en) 2020-08-27 2020-08-27 Machine vision-based steel coil abnormity identification method, system, equipment and medium

Country Status (1)

Country Link
CN (1) CN111968104B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112733841A (en) * 2020-12-30 2021-04-30 中冶赛迪重庆信息技术有限公司 Method, system, equipment and medium for judging internal disorder of steel coil
WO2023151248A1 (en) * 2022-02-10 2023-08-17 中冶南方工程技术有限公司 Steel coil height centering system based on image recognition

Citations (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4796209A (en) * 1986-06-26 1989-01-03 Allegheny Ludlum Corporation Random inventory system
TW200848175A (en) * 2007-06-08 2008-12-16 China Steel Corp Control system of edge guider and method used thereby
CN102722711A (en) * 2012-05-31 2012-10-10 信帧电子技术（北京）有限公司 License plate character sequence identification method and device in license plate type identification
CN102814340A (en) * 2011-06-08 2012-12-12 鞍钢股份有限公司 Intelligent study system and computational study method for hot rolled strip width control models
CN104683786A (en) * 2015-02-28 2015-06-03 上海玮舟微电子科技有限公司 Human eye tracking method and device of naked eye 3D equipment
CN104951741A (en) * 2014-03-31 2015-09-30 阿里巴巴集团控股有限公司 Character recognition method and device thereof
US20180114084A1 (en) * 2015-07-13 2018-04-26 Baidu Online Network Technology (Beijing) Co., Ltd Method for recognizing picture, method and apparatus for labelling picture, and storage medium
CN109002974A (en) * 2018-06-29 2018-12-14 首钢京唐钢铁联合有限责任公司 A kind of coil of strip surface quality grading determination method and device
CN109816645A (en) * 2019-01-18 2019-05-28 创新奇智(广州)科技有限公司 A kind of automatic testing method of coil of strip loose winding
CN110070281A (en) * 2019-04-12 2019-07-30 首钢京唐钢铁联合有限责任公司 A kind of vertical annealing furnace plan checking method and device
CN110110657A (en) * 2019-05-07 2019-08-09 中冶赛迪重庆信息技术有限公司 Method for early warning, device, equipment and the storage medium of visual identity danger
CN110414529A (en) * 2019-06-26 2019-11-05 深圳中兴网信科技有限公司 Paper information extracting method, system and computer readable storage medium
CN110695132A (en) * 2019-10-18 2020-01-17 首钢智新迁安电磁材料有限公司 Rewinding method and device of recoiling machine
CN110929756A (en) * 2019-10-23 2020-03-27 广物智钢数据服务(广州)有限公司 Deep learning-based steel size and quantity identification method, intelligent device and storage medium
CN111161260A (en) * 2020-01-02 2020-05-15 中冶赛迪重庆信息技术有限公司 Hot-rolled strip steel surface defect detection method and device based on deep learning
CN111232845A (en) * 2018-11-28 2020-06-05 周口师范学院 Steel coil crane automatic grabbing algorithm based on machine vision
CN111259908A (en) * 2020-03-24 2020-06-09 中冶赛迪重庆信息技术有限公司 Machine vision-based steel coil number identification method, system, equipment and storage medium
CN111311670A (en) * 2020-02-19 2020-06-19 中冶赛迪重庆信息技术有限公司 Cold bed top punching identification method, system and equipment based on image identification
CN111340027A (en) * 2020-03-05 2020-06-26 中冶赛迪重庆信息技术有限公司 Steel pile identification method and system, electronic equipment and medium
CN111524113A (en) * 2020-04-17 2020-08-11 中冶赛迪重庆信息技术有限公司 Lifting chain abnormity identification method, system, equipment and medium
CN111553950A (en) * 2020-04-30 2020-08-18 中冶赛迪重庆信息技术有限公司 Steel coil centering judgment method, system, medium and electronic terminal

Patent Citations (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4796209A (en) * 1986-06-26 1989-01-03 Allegheny Ludlum Corporation Random inventory system
TW200848175A (en) * 2007-06-08 2008-12-16 China Steel Corp Control system of edge guider and method used thereby
CN102814340A (en) * 2011-06-08 2012-12-12 鞍钢股份有限公司 Intelligent study system and computational study method for hot rolled strip width control models
CN102722711A (en) * 2012-05-31 2012-10-10 信帧电子技术（北京）有限公司 License plate character sequence identification method and device in license plate type identification
CN104951741A (en) * 2014-03-31 2015-09-30 阿里巴巴集团控股有限公司 Character recognition method and device thereof
CN104683786A (en) * 2015-02-28 2015-06-03 上海玮舟微电子科技有限公司 Human eye tracking method and device of naked eye 3D equipment
US20180114084A1 (en) * 2015-07-13 2018-04-26 Baidu Online Network Technology (Beijing) Co., Ltd Method for recognizing picture, method and apparatus for labelling picture, and storage medium
CN109002974A (en) * 2018-06-29 2018-12-14 首钢京唐钢铁联合有限责任公司 A kind of coil of strip surface quality grading determination method and device
CN111232845A (en) * 2018-11-28 2020-06-05 周口师范学院 Steel coil crane automatic grabbing algorithm based on machine vision
CN109816645A (en) * 2019-01-18 2019-05-28 创新奇智(广州)科技有限公司 A kind of automatic testing method of coil of strip loose winding
CN110070281A (en) * 2019-04-12 2019-07-30 首钢京唐钢铁联合有限责任公司 A kind of vertical annealing furnace plan checking method and device
CN110110657A (en) * 2019-05-07 2019-08-09 中冶赛迪重庆信息技术有限公司 Method for early warning, device, equipment and the storage medium of visual identity danger
CN110414529A (en) * 2019-06-26 2019-11-05 深圳中兴网信科技有限公司 Paper information extracting method, system and computer readable storage medium
CN110695132A (en) * 2019-10-18 2020-01-17 首钢智新迁安电磁材料有限公司 Rewinding method and device of recoiling machine
CN110929756A (en) * 2019-10-23 2020-03-27 广物智钢数据服务(广州)有限公司 Deep learning-based steel size and quantity identification method, intelligent device and storage medium
CN111161260A (en) * 2020-01-02 2020-05-15 中冶赛迪重庆信息技术有限公司 Hot-rolled strip steel surface defect detection method and device based on deep learning
CN111311670A (en) * 2020-02-19 2020-06-19 中冶赛迪重庆信息技术有限公司 Cold bed top punching identification method, system and equipment based on image identification
CN111340027A (en) * 2020-03-05 2020-06-26 中冶赛迪重庆信息技术有限公司 Steel pile identification method and system, electronic equipment and medium
CN111259908A (en) * 2020-03-24 2020-06-09 中冶赛迪重庆信息技术有限公司 Machine vision-based steel coil number identification method, system, equipment and storage medium
CN111524113A (en) * 2020-04-17 2020-08-11 中冶赛迪重庆信息技术有限公司 Lifting chain abnormity identification method, system, equipment and medium
CN111553950A (en) * 2020-04-30 2020-08-18 中冶赛迪重庆信息技术有限公司 Steel coil centering judgment method, system, medium and electronic terminal

Non-Patent Citations (12)

* Cited by examiner, † Cited by third party
Title
JULIO MOLLEDA等: "Optimizing Steel Coil Production: An Enhanced Inspection System Based on Anomaly Detection Techniques", 《IEEE INDUSTRY APPLICATIONS MAGAZINE》 *
YING LIANG等: "Mask Gradient Response-Based Threshold Segmentation for Surface Defect Detection of Milled Aluminum Ingot" *
冯谦等: "基于EAST 与CNN 的钢材表面字符检测与识别方法" *
刘英林等: "钢卷表面缺陷分布特征发现方法研究", 《冶金自动化》 *
周柳光等: "红外光电技术在热轧板带测宽中的应用", 《自动化仪表》 *
孙智慧等: "酸轧生产线改造中物料跟踪系统的研究与应用", 《自动化与仪表》 *
孙静全: "表面检测系统在热轧不锈钢检测的应用研究", 《中国优秀硕士学位论文全文数据库 工程科技I辑》 *
崔庆胜等: "红外测宽技术及其在热轧带钢宽度检测中的应用", 《仪表技术与传感器》 *
张轶鑫: "基于图像分割和模式识别的钢材断口图像分析方法研究" *
潘毓淇: "带钢瓢曲检测方法研究及监控系统的实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
王少等: "热轧板带表面质量智能化自动判定系统的开发应用" *
陈刚: "伞杆加工过程中的机器视觉检测系统研究" *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112733841A (en) * 2020-12-30 2021-04-30 中冶赛迪重庆信息技术有限公司 Method, system, equipment and medium for judging internal disorder of steel coil
CN112733841B (en) * 2020-12-30 2022-12-16 中冶赛迪信息技术(重庆)有限公司 Method, system, equipment and medium for judging internal disorder of steel coil
WO2023151248A1 (en) * 2022-02-10 2023-08-17 中冶南方工程技术有限公司 Steel coil height centering system based on image recognition

Also Published As

Publication number Publication date
CN111968104B (en) 2023-04-07

Similar Documents

Publication Publication Date Title
CN108009515B (en) Power transmission line positioning and identifying method of unmanned aerial vehicle aerial image based on FCN
US20200372248A1 (en) Certificate recognition method and apparatus, electronic device, and computer-readable storage medium
CN111968104B (en) Machine vision-based steel coil abnormity identification method, system, equipment and medium
CN112132523B (en) Method, system and device for determining quantity of goods
CN113111844B (en) Operation posture evaluation method and device, local terminal and readable storage medium
CN111340027A (en) Steel pile identification method and system, electronic equipment and medium
CN111639629B (en) Pig weight measurement method and device based on image processing and storage medium
CN113962306A (en) Image processing method, image processing device, electronic equipment and computer readable storage medium
CN111539938A (en) Method, system, medium and electronic terminal for detecting curvature of rolled strip steel strip head
CN111898610B (en) Card unfilled corner detection method, device, computer equipment and storage medium
CN110796709A (en) Method and device for acquiring size of frame number, computer equipment and storage medium
CN112683169A (en) Object size measuring method, device, equipment and storage medium
CN110991201B (en) Bar code detection method and related device
CN113177941B (en) Steel coil edge crack identification method, system, medium and terminal
CN112749735B (en) Converter tapping steel flow identification method, system, medium and terminal based on deep learning
CN114359172A (en) Cigarette carton multi-face detection and identification method and system under stock or display scene
CN114037987A (en) Intelligent identification method, device, medium and equipment for scrap steel
CN112053333A (en) Square billet detection method, system, equipment and medium based on machine vision
CN113592839A (en) Distribution network line typical defect diagnosis method and system based on improved fast RCNN
CN113221812A (en) Training method of face key point detection model and face key point detection method
CN110955797B (en) User position determining method, device, electronic equipment and storage medium
CN112651315A (en) Information extraction method and device of line graph, computer equipment and storage medium
CN115619791B (en) Article display detection method, device, equipment and readable storage medium
CN111860035A (en) Book cover detection method and device, storage medium and electronic equipment
CN116091998A (en) Image processing method, device, computer equipment and storage medium

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
CB02 Change of applicant information

Address after: 401329 No. 5-6, building 2, No. 66, Nongke Avenue, Baishiyi Town, Jiulongpo District, Chongqing

Applicant after: MCC CCID information technology (Chongqing) Co.,Ltd.

Address before: 20-24 / F, No.7 Longjing Road, North New District, Yubei District, Chongqing

Applicant before: CISDI CHONGQING INFORMATION TECHNOLOGY Co.,Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant