CN112308072A - Scattered blanking identification method and system for scrap steel yard, electronic equipment and medium - Google Patents

Scattered blanking identification method and system for scrap steel yard, electronic equipment and medium Download PDF

Info

Publication number
CN112308072A
CN112308072A CN202011232211.XA CN202011232211A CN112308072A CN 112308072 A CN112308072 A CN 112308072A CN 202011232211 A CN202011232211 A CN 202011232211A CN 112308072 A CN112308072 A CN 112308072A
Authority
CN
China
Prior art keywords
scattered
coordinate system
blanking
interest
region
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
CN202011232211.XA
Other languages
Chinese (zh)
Other versions
CN112308072B (en
Inventor
庞殊杨
毛尚伟
袁钰博
刘斌
李语桐
李昕祎
龚强
李邈
贾鸿盛
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 CN202011232211.XA priority Critical patent/CN112308072B/en
Publication of CN112308072A publication Critical patent/CN112308072A/en
Application granted granted Critical
Publication of CN112308072B publication Critical patent/CN112308072B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Geometry (AREA)
  • Image Analysis (AREA)
  • General Factory Administration (AREA)

Abstract

The invention provides a scattered blanking identification method, a scattered blanking identification system, electronic equipment and a medium for a scrap steel stock yard, wherein the method comprises the following steps: arranging a camera above the stock ground, wherein the camera moves and collects an interested area; setting the plane of the stock yard as a first coordinate system, and setting the plane of the region of interest as a second coordinate system; determining scattered blanking through the region of interest and confirming the position of the scattered blanking in a second coordinate system; and determining the positions of the scattered blanking on the first coordinate system and the stock ground according to the position relationship between the first coordinate system and the second coordinate system. The camera is arranged on the stock ground, the view field of the camera is set as an interested area, the target identification of scattered blanking is carried out in the interested area, the position of the scattered blanking in the interested area is determined, the actual position of the scattered blanking is determined according to the corresponding relation between the interested area and the stock ground, and the scattered blanking is convenient to position and confirm.

Description

Scattered blanking identification method and system for scrap steel yard, electronic equipment and medium
Technical Field
The invention relates to the technical field of image recognition, in particular to a scattered blanking recognition method and system for a scrap steel yard, electronic equipment and a medium.
Background
In the process of steel smelting, scrap steel needs to be recovered and reused. However, in the loading and unloading process of the scrap yard, the ground may have loose materials that may drop off accidentally, so the loose materials on the ground need to be picked up in time. Because scattered scrap steel is more, and equipment reciprocating motion, scattered material position is not fixed, if only adopt manual identification, the condition that probably exists omission test, wrong detection, not only detection efficiency is low, and consume a large amount of costs of labor.
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, an electronic device and a medium for identifying scattered and fallen materials in a scrap yard, which are used to solve the problem of inconvenient manual detection of scattered and fallen materials in the prior art.
In order to achieve the above objects and other related objects, the present invention provides a scattered blanking identification method for a scrap steel yard, comprising:
arranging a camera above the stock ground, wherein the camera moves and collects an interested area;
setting the plane of the stock yard as a first coordinate system, and setting the plane of the region of interest as a second coordinate system;
determining scattered blanking through the region of interest and confirming the position of the scattered blanking in a second coordinate system;
and determining the positions of the scattered blanking on the first coordinate system and the stock ground according to the position relationship between the first coordinate system and the second coordinate system.
Optionally, the step of determining scattered blanking through the region of interest includes:
marking the scattered materials in the region of interest to obtain a data set and a training set;
inputting the training set into a neural network for training to obtain a training model;
and determining the scattered materials in the region of interest through the training model.
Carrying out edge detection on the region of interest and extracting image features of the region of interest;
extracting the outline of the image after the edge detection, and extracting the outline of an object in the region of interest;
and determining the scattered materials in the region of interest according to the direction and the shape of the outline of the region of interest.
If scattered blanking is identified by the training model and the outline characteristic judgment, the scattered blanking in the region of interest can be determined;
if the training model identifies scattered blanking and the outline characteristic judges that scattered blanking is not identified, determining the scattered blanking in the region of interest according to the identification confidence of the training model;
if the training model does not recognize the scattered blanking, the contour characteristic judgment recognizes the scattered blanking, and then the scattered blanking in the region of interest can be determined according to the contour characteristic.
Optionally, the step of determining the positions of the scattered blanking materials on the first coordinate system and the stock yard through the position relationship between the first coordinate system and the second coordinate system includes:
determining the position coordinate of the center of the interested area on the first coordinate system through any point of the first coordinate system, wherein the mathematical expression of the position coordinate of the center of the interested area on the first coordinate system is as follows:
[camerax,cameray]
wherein, cameraxIs the position coordinate of the center of the region of interest on the X-axis of the first coordinate system, camerayA position coordinate of the center of the region of interest on the Y axis on the first coordinate system;
the mathematical expression of the position coordinates of the scattered blanking materials on the second coordinate system is as follows:
Figure BDA0002765576600000021
wherein steelNxminFor the smallest position coordinate of the scattered material on the X-axis of the second coordinate system, steelNyminFor the minimum position coordinate of the scattered material on the Y axis of the second coordinate system, steelNxmaxFor the maximum position coordinate of the scattered material on the X-axis of the second coordinate system, steelNymaxThe maximum position coordinate of the scattered blanking on the Y axis on a second coordinate system is shown, and N is the serial number of the scattered blanking;
the mathematical expression of the position coordinates of the scattered blanking materials on the first coordinate system is as follows:
Figure BDA0002765576600000022
wherein k is a proportionality coefficient.
Optionally, the determining process of the scaling factor is as follows: and acquiring the pixel area of the interested area and the actual area of the stock ground, and determining the proportionality coefficient according to the ratio of the pixel area to the actual area of the stock ground.
Optionally, the edge detection operator or the filter includes a Canny operator, a Sobel operator, a Laplacian operator, a Scharr filter, and the like.
Optionally, the contour of the image after the edge detection is extracted, and the contour of the object in the region of interest is extracted. Setting a scattered blanking length threshold value L and a width threshold value W for the rectangular outline, if the length of the outline of the object in the region of interest is less than L and the width of the object in the region of interest is less than W, determining that the outline is the rectangular scattered blanking outline of the region of interest, and returning the position coordinates of the scattered blanking on a first coordinate system; and for the irregular contour, setting a scattered blanking area threshold value A, if the closed area of the contour of the object in the region of interest is smaller than A, determining the contour as the irregular scattered blanking contour of the region of interest, and returning the position coordinates of the scattered blanking on the first coordinate system.
Optionally, if the training model identifies scattered blanking, and the contour feature judges that the scattered blanking is not identified, setting an identification confidence threshold T, and according to the fact that the confidence of the identification result of the training model is greater than T, determining that the object is scattered blanking, and returning the position coordinates of the scattered blanking on the first coordinate system.
Optionally, a camera is disposed above the stock yard, and the step of moving the camera and acquiring the region of interest includes:
the camera is arranged above the stock ground and is in linear stepping reciprocating motion above the stock ground, and the emotional required area is collected.
A scrap yard scatter identification system, comprising:
the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for arranging a camera above a stock ground, and the camera moves and acquires an interested area;
the identification module is used for setting the plane of the stock yard as a first coordinate system, setting the plane of the interested area as a second coordinate system, determining scattered blanking through the interested area and confirming the position of the scattered blanking in the second coordinate system;
and the processing module is used for determining the positions of the scattered blanking materials on the first coordinate system and the stock ground according to the position relation between the first coordinate system and the second coordinate system.
Optionally, the method includes:
the step of determining scattered blanking through the region of interest comprises:
marking the scattered materials in the region of interest to obtain a data set and a training set;
inputting the training set into a neural network for training to obtain a training model;
and determining the scattered materials in the region of interest through the training model.
Carrying out edge detection on the region of interest and extracting image features of the region of interest;
extracting the outline of the image after the edge detection, and extracting the outline of an object in the region of interest;
and determining the scattered materials in the region of interest according to the direction and the shape of the outline of the region of interest.
If scattered blanking is identified by the training model and the outline characteristic judgment, the scattered blanking in the region of interest can be determined;
if the training model identifies scattered blanking and the outline characteristic judges that scattered blanking is not identified, determining the scattered blanking in the region of interest according to the identification confidence of the training model;
if the training model does not recognize the scattered blanking, the contour characteristic judgment recognizes the scattered blanking, and then the scattered blanking in the region of interest can be determined according to the contour characteristic.
Optionally, the step of determining the positions of the scattered blanking materials on the first coordinate system and the stock yard through the position relationship between the first coordinate system and the second coordinate system includes:
determining the position coordinate of the center of the interested area on the first coordinate system through any point of the first coordinate system, wherein the mathematical expression of the position coordinate of the center of the interested area on the first coordinate system is as follows:
[camerax,cameray]
wherein, cameraxOf a region of interestPosition coordinates of the center on the X-axis of said first coordinate system, camerayA position coordinate of the center of the region of interest on the Y axis on the first coordinate system;
the mathematical expression of the position coordinates of the scattered blanking materials on the second coordinate system is as follows:
Figure BDA0002765576600000041
wherein steelNxminFor the smallest position coordinate of the scattered material on the X-axis of the second coordinate system, steelNyminFor the minimum position coordinate of the scattered material on the Y axis of the second coordinate system, steelNxmaxFor the maximum position coordinate of the scattered material on the X-axis of the second coordinate system, steelNymaxThe maximum position coordinate of the scattered blanking on the Y axis on a second coordinate system is shown, and N is the serial number of the scattered blanking;
the mathematical expression of the position coordinates of the scattered blanking materials on the first coordinate system is as follows:
Figure BDA0002765576600000042
wherein k is a proportionality coefficient.
Optionally, the edge detection operator or the filter includes a Canny operator, a Sobel operator, a Laplacian operator, a Scharr filter, and the like.
Optionally, the contour of the image after the edge detection is extracted, and the contour of the object in the region of interest is extracted. Setting a scattered blanking length threshold value L and a width threshold value W for the rectangular outline, if the length of the outline of the object in the region of interest is less than L and the width of the object in the region of interest is less than W, determining that the outline is the rectangular scattered blanking outline of the region of interest, and returning the position coordinates of the scattered blanking on a first coordinate system; and for the irregular contour, setting a scattered blanking area threshold value A, if the closed area of the contour of the object in the region of interest is smaller than A, determining the contour as the irregular scattered blanking contour of the region of interest, and returning the position coordinates of the scattered blanking on the first coordinate system.
Optionally, if the training model identifies scattered blanking, and the contour feature judges that the scattered blanking is not identified, setting an identification confidence threshold T, and according to the fact that the confidence of the identification result of the training model is greater than T, determining that the object is scattered blanking, and returning the position coordinates of the scattered blanking on the first coordinate system.
An electronic device, 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 electronic device to perform one or more of the methods.
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 described methods.
As mentioned above, the scattered blanking identification method, system, electronic equipment and medium for the steel scrap yard have the following beneficial effects:
the camera is arranged on the stock ground, the view field of the camera is set as an interested area, the target identification of scattered blanking is carried out in the interested area, the position of the scattered blanking in the interested area is determined, the actual position of the scattered blanking is determined according to the corresponding relation between the interested area and the stock ground, the positioning and confirmation of the scattered blanking are facilitated, the detection efficiency and the accuracy are improved, and the system error existing in manual detection is reduced.
Drawings
Fig. 1 is a schematic diagram illustrating a scattered blanking identification method for a scrap yard according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a scattered blanking identification system of a scrap yard according to an embodiment of the present invention.
Fig. 3 is a schematic diagram showing a camera moving and acquiring a region of interest according to an embodiment of the present invention.
Fig. 4 is a schematic diagram illustrating the coordinate positions of the scattered blanking material according to the 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 scattered blanking identification method for a scrap yard, comprising:
s1: a camera is arranged above a stock ground, moves and collects a Region of Interest (ROI);
s2: setting the plane of the stock yard as a first coordinate system, and setting the plane of the region of interest as a second coordinate system;
s3: determining scattered blanking through the region of interest and confirming the position of the scattered blanking in a second coordinate system;
s4: and determining the positions of the scattered blanking on the first coordinate system and the stock ground according to the position relationship between the first coordinate system and the second coordinate system. The camera is arranged on the stock ground, the view field of the camera is set as an interested area, the target identification of scattered blanking is carried out in the interested area, the position of the scattered blanking in the interested area is determined, the actual position of the scattered blanking is determined according to the corresponding relation between the interested area and the stock ground, the positioning and confirmation of the scattered blanking are facilitated, the detection efficiency and the accuracy are improved, and the system error existing in manual detection is reduced.
In some implementations, the step of determining a scattered blanking from the region of interest includes:
marking the scattered materials in the region of interest to obtain a data set and a training set, and also performing framing on marked positions, framing out the positions of the scattered materials in the region of interest, recording position information of a target rectangular frame corresponding to the framing, and obtaining a corresponding data set and a corresponding training set, and further including a verification set;
inputting the training set into a neural network for training to obtain a training model, wherein the neural network can select a convolutional neural network, learning and training the characteristics of the object in the target frame in each region of interest through the convolutional neural network for target detection to finally obtain a scattered material target detection model, and the convolutional neural network can comprise at least one of the following components: SSD-MobileNet, R-CNN, Faster-RCNN, and YOLO series. Further, the contour feature judgment can be performed, including:
carrying out edge detection on the region of interest and extracting image features of the region of interest;
extracting the outline of the image after the edge detection, and extracting the outline of an object in the region of interest;
determining scattered materials in the region of interest according to the direction and the shape of the outline of the region of interest;
if scattered blanking is identified by the training model and the outline characteristic judgment, the scattered blanking in the region of interest can be determined;
if the training model identifies scattered blanking and the outline characteristic judges that scattered blanking is not identified, determining the scattered blanking in the region of interest according to the identification confidence of the training model;
if the training model does not recognize the scattered blanking, the contour characteristic judgment recognizes the scattered blanking, and then the scattered blanking in the region of interest can be determined according to the contour characteristic.
Referring to fig. 3 and 4, the camera 4 is arranged on the traveling frame 1, and the unmanned vehicle 3 can drive the camera 4 to perform linear stepping reciprocating motion on the track 2, so as to acquire and traverse images of the stock ground 4;
the step of determining the positions of the scattered blanking on the first coordinate system and the stock ground according to the position relationship between the first coordinate system and the second coordinate system comprises the following steps:
determining the position coordinate of the center of the interested area on the first coordinate system through any point of the first coordinate system, wherein the mathematical expression of the position coordinate of the center of the interested area on the first coordinate system is as follows:
[camerax,cameray]
wherein, cameraxIs the position coordinate of the center of the region of interest on the X-axis of the first coordinate system, camerayA position coordinate of the center of the region of interest on the Y axis on the first coordinate system;
the mathematical expression of the position coordinates of the scattered blanking materials on the second coordinate system is as follows:
Figure BDA0002765576600000071
wherein steelNxminFor the smallest position coordinate of the scattered material on the X-axis of the second coordinate system, steelNyminFor the minimum position coordinate of the scattered material on the Y axis of the second coordinate system, steelNxmaxFor the maximum position coordinate of the scattered material on the X-axis of the second coordinate system, steelNymaxThe maximum position coordinate of the scattered blanking material on the Y axis on a second coordinate system is shown, N isNumbering the scattered blanking;
the mathematical expression of the position coordinates of the scattered blanking materials on the first coordinate system is as follows:
Figure BDA0002765576600000072
wherein k is a proportionality coefficient.
Further, the determining process of the scaling factor is as follows: obtaining a pixel area of the region of interest and an actual area of the stock yard, and determining the proportionality coefficient according to a ratio of the pixel area to the actual area of the stock yard, for example: 1 pixel corresponds to k centimeters above the actual ground, and its expression is:
1pixel＝k cm
the adopted edge detection operators or filters comprise Canny operators, Sobel operators, Laplacian operators, Scharr filters and the like.
Further, contour extraction is carried out on the image after the edge detection, and the contour of the object in the region of interest is extracted. Setting a scattered blanking length threshold value L and a width threshold value W for the rectangular outline, if the length of the outline of the object in the region of interest is less than L and the width of the object in the region of interest is less than W, determining that the outline is the rectangular scattered blanking outline of the region of interest, and returning the position coordinates of the scattered blanking on a first coordinate system; and for the irregular contour, setting a scattered blanking area threshold value A, if the closed area of the contour of the object in the region of interest is smaller than A, determining the contour as the irregular scattered blanking contour of the region of interest, and returning the position coordinates of the scattered blanking on the first coordinate system.
And if the training model identifies scattered blanking and the outline characteristic judges that the scattered blanking is not identified, setting an identification confidence threshold T, and if the confidence of the identification result of the training model is greater than T, determining that the object is scattered blanking, and returning the position coordinates of the scattered blanking on the first coordinate system.
In some implementations, positioning a camera above the yard, the camera moving and acquiring the region of interest includes:
the camera is arranged above the stock ground and is in linear stepping reciprocating motion above the stock ground, and the emotional required area is collected.
Referring to fig. 2, the present invention provides a system for identifying scattered materials in a waste material yard, comprising:
the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for arranging a camera above a stock ground, and the camera moves and acquires an interested area;
the identification module is used for setting the plane of the stock yard as a first coordinate system, setting the plane of the interested area as a second coordinate system, determining scattered blanking through the interested area and confirming the position of the scattered blanking in the second coordinate system;
and the processing module is used for determining the positions of the scattered blanking materials on the first coordinate system and the stock ground according to the position relation between the first coordinate system and the second coordinate system.
Optionally, the method includes:
the step of determining scattered blanking through the region of interest comprises:
marking the scattered materials in the region of interest to obtain a data set and a training set;
inputting the training set into a neural network for training to obtain a training model;
and determining the scattered materials in the region of interest through the training model.
Optionally, the step of determining the positions of the scattered blanking materials on the first coordinate system and the stock yard through the position relationship between the first coordinate system and the second coordinate system includes:
determining the position coordinate of the center of the interested area on the first coordinate system through any point of the first coordinate system, wherein the mathematical expression of the position coordinate of the center of the interested area on the first coordinate system is as follows:
[camerax,cameray]
wherein, cameraxIs the position coordinate of the center of the region of interest on the X-axis of the first coordinate system, camerayA position coordinate of the center of the region of interest on the Y axis on the first coordinate system;
the mathematical expression of the position coordinates of the scattered blanking materials on the second coordinate system is as follows:
Figure BDA0002765576600000081
wherein steelNxminFor the smallest position coordinate of the scattered material on the X-axis of the second coordinate system, steelNyminFor the minimum position coordinate of the scattered material on the Y axis of the second coordinate system, steelNxmaxFor the maximum position coordinate of the scattered material on the X-axis of the second coordinate system, steelNymaxThe maximum position coordinate of the scattered blanking on the Y axis on a second coordinate system is shown, and N is the serial number of the scattered blanking;
the mathematical expression of the position coordinates of the scattered blanking materials on the first coordinate system is as follows:
Figure BDA0002765576600000091
wherein k is a proportionality coefficient.
The adopted edge detection operators or filters comprise Canny operators, Sobel operators, Laplacian operators, Scharr filters and the like.
Further, contour extraction is carried out on the image after the edge detection, and the contour of the object in the region of interest is extracted. Setting a scattered blanking length threshold value L and a width threshold value W for the rectangular outline, if the length of the outline of the object in the region of interest is less than L and the width of the object in the region of interest is less than W, determining that the outline is the rectangular scattered blanking outline of the region of interest, and returning the position coordinates of the scattered blanking on a first coordinate system; and for the irregular contour, setting a scattered blanking area threshold value A, if the closed area of the contour of the object in the region of interest is smaller than A, determining the contour as the irregular scattered blanking contour of the region of interest, and returning the position coordinates of the scattered blanking on the first coordinate system.
And if the training model identifies scattered blanking and the outline characteristic judges that the scattered blanking is not identified, setting an identification confidence threshold T, and if the confidence of the identification result of the training model is greater than T, determining that the object is scattered blanking, and returning the position coordinates of the scattered blanking on the first coordinate system.
An embodiment of the present invention provides an electronic device, 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 scattered blanking identification method for a scrap steel stock yard is characterized by comprising the following steps:
arranging a camera above the stock ground, wherein the camera moves and collects an interested area;
setting the plane of the stock yard as a first coordinate system, and setting the plane of the region of interest as a second coordinate system;
determining scattered blanking through the region of interest and confirming the position of the scattered blanking in a second coordinate system;
and determining the positions of the scattered blanking on the first coordinate system and the stock ground according to the position relationship between the first coordinate system and the second coordinate system.
2. The scattered blanking identification method for the steel scrap yard according to claim 1, wherein the step of determining the scattered blanking through the region of interest comprises:
marking the scattered materials in the region of interest to obtain a data set and a training set;
inputting the training set into a neural network for training to obtain a training model;
determining scattered materials in the region of interest through the training model;
carrying out edge detection on the region of interest and extracting image features of the region of interest;
extracting the outline of the image after the edge detection, and extracting the outline of an object in the region of interest;
determining scattered materials in the region of interest according to the direction and the shape of the outline of the region of interest;
if scattered blanking is identified by the training model and the outline characteristic judgment, the scattered blanking in the region of interest can be determined;
if the training model identifies scattered blanking and the outline characteristic judges that scattered blanking is not identified, determining the scattered blanking in the region of interest according to the identification confidence of the training model;
if the training model does not recognize the scattered blanking, the contour characteristic judgment recognizes the scattered blanking, and then the scattered blanking in the region of interest can be determined according to the contour characteristic.
3. The scattered blanking identification method for the scrap steel yard according to claim 1, wherein the step of determining the positions of the scattered blanking on the first coordinate system and the yard through the position relationship between the first coordinate system and the second coordinate system comprises:
determining the position coordinate of the center of the interested area on the first coordinate system through any point of the first coordinate system, wherein the mathematical expression of the position coordinate of the center of the interested area on the first coordinate system is as follows:
[camerax,cameray]
wherein, cameraxIs the position coordinate of the center of the region of interest on the X-axis of the first coordinate system, camerayA position coordinate of the center of the region of interest on the Y axis on the first coordinate system;
the mathematical expression of the position coordinates of the scattered blanking materials on the second coordinate system is as follows:
Figure FDA0002765576590000021
wherein steelNxminFor the smallest position coordinate of the scattered material on the X-axis of the second coordinate system, steelNyminFor the minimum position coordinate of the scattered material on the Y axis of the second coordinate system, steelNxmaxFor the maximum position coordinate of the scattered material on the X-axis of the second coordinate system, steelNymaxThe maximum position coordinate of the scattered blanking on the Y axis on a second coordinate system is shown, and N is the serial number of the scattered blanking;
the mathematical expression of the position coordinates of the scattered blanking materials on the first coordinate system is as follows:
Figure FDA0002765576590000022
wherein k is a proportionality coefficient.
4. The scattered blanking identification method for the steel scrap yard according to claim 3, wherein the determination process of the proportionality coefficient is as follows: and acquiring the pixel area of the interested area and the actual area of the stock ground, and determining the proportionality coefficient according to the ratio of the pixel area to the actual area of the stock ground.
5. The scattered blanking identification method for the steel scrap yard according to claim 2, characterized in that the contour extraction is performed on the image after the edge detection, the contour of the object in the region of interest is extracted, for the rectangular contour, a scattered blanking length threshold value L and a width threshold value W are set, if the length of the contour of the object in the region of interest is less than L and the width of the object in the region of interest is less than W, the contour is determined to be the rectangular scattered blanking contour of the region of interest, and the position coordinates of the scattered blanking on the first coordinate system are returned; and for the irregular contour, setting a scattered blanking area threshold value A, if the closed area of the contour of the object in the region of interest is smaller than A, determining the contour as the irregular scattered blanking contour of the region of interest, and returning the position coordinates of the scattered blanking on the first coordinate system.
6. The method for recognizing scattered blanking of the steel scrap yard according to claim 2, wherein if the training model recognizes scattered blanking and the contour feature judges that the scattered blanking is not recognized, a recognition confidence threshold T is set, and if the confidence is greater than T according to the recognition result of the training model, the object is considered as scattered blanking, and the position coordinates of the scattered blanking on the first coordinate system are returned.
7. The scattered blanking identification method for the scrap steel yard according to claim 1, wherein a camera is arranged above the yard, and the step of moving the camera and collecting the interested area comprises the following steps:
and arranging the camera above the stock ground, wherein the camera makes linear stepping reciprocating motion above the stock ground and collects an interested area.
8. A scrap yard spill identification system as claimed in any one of claims 1 to 7, comprising:
the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for arranging a camera above a stock ground, and the camera moves and acquires an interested area;
the identification module is used for setting the plane of the stock yard as a first coordinate system, setting the plane of the interested area as a second coordinate system, determining scattered blanking through the interested area and confirming the position of the scattered blanking in the second coordinate system;
the processing module is used for determining the positions of the scattered blanking materials on the first coordinate system and the stock ground according to the position relation between the first coordinate system and the second coordinate system;
the acquisition module, the identification module and the processing module are connected.
9. An electronic device, 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.
CN202011232211.XA 2020-11-06 2020-11-06 Scrap steel stock yard scattered material identification method, system, electronic equipment and medium Active CN112308072B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011232211.XA CN112308072B (en) 2020-11-06 2020-11-06 Scrap steel stock yard scattered material identification method, system, electronic equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011232211.XA CN112308072B (en) 2020-11-06 2020-11-06 Scrap steel stock yard scattered material identification method, system, electronic equipment and medium

Publications (2)

Publication Number Publication Date
CN112308072A true CN112308072A (en) 2021-02-02
CN112308072B CN112308072B (en) 2023-05-12

Family

ID=74326509

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011232211.XA Active CN112308072B (en) 2020-11-06 2020-11-06 Scrap steel stock yard scattered material identification method, system, electronic equipment and medium

Country Status (1)

Country Link
CN (1) CN112308072B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105335973A (en) * 2015-10-20 2016-02-17 上海交通大学 Visual processing method for strip steel processing production line
CN106382930A (en) * 2016-08-18 2017-02-08 广东工业大学 An indoor AGV wireless navigation method and a device therefor
CN107444998A (en) * 2016-05-31 2017-12-08 株式会社日立制作所 Conveying equipment control system and conveying equipment control method
CN107844750A (en) * 2017-10-19 2018-03-27 华中科技大学 A kind of water surface panoramic picture target detection recognition methods
CN108364287A (en) * 2018-02-11 2018-08-03 北京简易科技有限公司 A kind of monitoring foreign bodies method, apparatus and stamping system
CN108356422A (en) * 2017-01-23 2018-08-03 宝山钢铁股份有限公司 The on-line measurement of band volume continuous laser blanking, waste material are fallen and finished product separation recognition methods
US20190130215A1 (en) * 2016-04-21 2019-05-02 Osram Gmbh Training method and detection method for object recognition
CN110136264A (en) * 2019-05-30 2019-08-16 北京中盛博方环保工程技术有限公司 The modeling method and system of stock ground material based on 3 D laser scanning
CN110968110A (en) * 2018-09-29 2020-04-07 广州极飞科技有限公司 Method and device for determining operation area, unmanned aerial vehicle and storage medium
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

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105335973A (en) * 2015-10-20 2016-02-17 上海交通大学 Visual processing method for strip steel processing production line
US20190130215A1 (en) * 2016-04-21 2019-05-02 Osram Gmbh Training method and detection method for object recognition
CN107444998A (en) * 2016-05-31 2017-12-08 株式会社日立制作所 Conveying equipment control system and conveying equipment control method
CN106382930A (en) * 2016-08-18 2017-02-08 广东工业大学 An indoor AGV wireless navigation method and a device therefor
CN108356422A (en) * 2017-01-23 2018-08-03 宝山钢铁股份有限公司 The on-line measurement of band volume continuous laser blanking, waste material are fallen and finished product separation recognition methods
CN107844750A (en) * 2017-10-19 2018-03-27 华中科技大学 A kind of water surface panoramic picture target detection recognition methods
CN108364287A (en) * 2018-02-11 2018-08-03 北京简易科技有限公司 A kind of monitoring foreign bodies method, apparatus and stamping system
CN110968110A (en) * 2018-09-29 2020-04-07 广州极飞科技有限公司 Method and device for determining operation area, unmanned aerial vehicle and storage medium
CN110136264A (en) * 2019-05-30 2019-08-16 北京中盛博方环保工程技术有限公司 The modeling method and system of stock ground material based on 3 D laser scanning
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

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
DR. M. P. CHITRA 等: "Object Identification in Steel Container through Thermal Image Pixel Analysis", 《INTERNATIONAL RESEARCH JOURNAL OF ENGINEERING AND TECHNOLOGY (IRJET)》 *
田明锐 等: "基于机器视觉的沥青混凝土卸料装车研究", 《中国工程机械学报》 *
豆秀梅 等: "基于高清摄像机的高速公路路面散落物自动检测方法研究", 《地理信息世界》 *

Also Published As

Publication number Publication date
CN112308072B (en) 2023-05-12

Similar Documents

Publication Publication Date Title
CN111382704B (en) Vehicle line pressing violation judging method and device based on deep learning and storage medium
CN107123188B (en) Wound ticket identification and positioning method based on template matching algorithm and edge features
CN112102369B (en) Autonomous inspection method, device, equipment and storage medium for water surface floating target
CN111259889A (en) Image text recognition method and device, computer equipment and computer storage medium
CN108564579B (en) Concrete crack detection method and detection device based on time-space correlation
CN112308003B (en) Method, system, equipment and medium for identifying loading state of scrap steel wagon
CN114049624B (en) Ship cabin intelligent detection method and system based on machine vision
CN112621765B (en) Automatic equipment assembly control method and device based on manipulator
CN112070117A (en) Belt tearing detection method and device and storage medium
Xiao et al. A real-time system for lane detection based on FPGA and DSP
CN112308848A (en) Method and system for identifying state of baffle plate of scrap steel truck, electronic equipment and medium
CN111968104B (en) Machine vision-based steel coil abnormity identification method, system, equipment and medium
CN112561885B (en) YOLOv 4-tiny-based gate valve opening detection method
CN112308072A (en) Scattered blanking identification method and system for scrap steel yard, electronic equipment and medium
CN115984806B (en) Dynamic detection system for road marking damage
CN107563282A (en) For unpiloted recognition methods, electronic equipment, storage medium and system
CN114494355A (en) Trajectory analysis method and device based on artificial intelligence, terminal equipment and medium
CN114187269A (en) Method for rapidly detecting surface defect edge of small-sized device
CN111476770A (en) Slag detection method, device, equipment and medium based on image processing
CN112329849A (en) Scrap steel stock yard unloading state identification method based on machine vision, medium and terminal
CN112712539B (en) Machine vision-based converter tapping buggy ladle control method, system, medium and terminal
CN112308073B (en) Method, system, equipment and medium for identifying loading and unloading and transferring states of scrap steel train
CN113822396B (en) Bridge crane real-time positioning method, device and system
Baniadamdizaj et al. Document Localization in Images Taken by Smartphones Using a Fully Convolutional Neural Network
CN113628238B (en) Target object positioning method, device and 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
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.

GR01 Patent grant
GR01 Patent grant