CN112037199A - Hot rolled bar collecting and finishing roller way blanking detection method, system, medium and terminal - Google Patents
Hot rolled bar collecting and finishing roller way blanking detection method, system, medium and terminal Download PDFInfo
- Publication number
- CN112037199A CN112037199A CN202010896107.4A CN202010896107A CN112037199A CN 112037199 A CN112037199 A CN 112037199A CN 202010896107 A CN202010896107 A CN 202010896107A CN 112037199 A CN112037199 A CN 112037199A
- Authority
- CN
- China
- Prior art keywords
- bar
- roller way
- hot
- target
- point1
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000007689 inspection Methods 0.000 claims abstract description 17
- 238000002372 labelling Methods 0.000 claims abstract description 16
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000004590 computer program Methods 0.000 claims description 14
- 238000005098 hot rolling Methods 0.000 claims description 10
- 230000003068 static effect Effects 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000000926 separation method Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 2
- 238000013135 deep learning Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/30204—Marker
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a hot rolled bar collecting and finishing roller way blanking detection method, a system, a medium and a terminal, wherein the method comprises the following steps: acquiring image information of a roller way for collecting hot-rolled bars; setting an interested area according to the position of the output roller way of the inspection rack; labeling scattered bars to obtain a data set; establishing a hot-rolled bar target detection model and training the hot-rolled bar target detection model; acquiring real-time image data, inputting the real-time image data into a trained hot-rolled bar target detection model, and acquiring a recognition result; judging whether scattered bars exist on an output roller way of the inspection bench or not according to the identification result, and finishing the collection of the hot rolled bars and finishing the detection of the blanking of the roller way; according to the invention, the neural network and deep learning are utilized, the scattering condition of the hot rolled bars in the picture can be identified in real time, and the warning signal is returned when the scattered bars are detected, so that the conditions of missing detection and wrong detection caused by manual identification are avoided, and the safety and accuracy of the hot rolled bar collection and roller way blanking detection are improved.
Description
Technical Field
The invention relates to the field of metallurgy and the field of image recognition, in particular to a hot-rolled bar collection completion roller bed blanking detection method, a system, a medium and a terminal.
Background
In the hot rolling production link, the rods on the rack roller way need to be bundled, and if blanking appears on the collection completion roller way, the normal bundling of the rods can be influenced. In order to ensure continuous and smooth operation of the link, the condition of scattered bars in the roller way of the output rack needs to be checked in real time.
At present, the hot rolled bar is collected and the roller way blanking detection is completed mainly through the identification of experienced workers. However, due to the fact that the production line is large in number and long in production time, if manual identification is only relied on, the situations of missing detection and error detection may exist. Therefore, an automatic detection system is urgently needed to replace manual identification, realize the real-time detection of the scattered bars on the rack roller way, and return a warning signal when detecting the scattered bars to remind operating personnel to process.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present invention provides a method, a system, a medium and a terminal for detecting the hot rolled bar material falling from the roller way after collecting the hot rolled bar material, so as to solve the above-mentioned technical problems.
The invention provides a hot rolled bar collecting and finishing roller way blanking detection method, which comprises the following steps:
acquiring image information of a roller way for collecting hot-rolled bars;
checking the position of a table frame output roller way according to the image information, and setting an interested area;
labeling scattered bars in the image information to obtain a data set;
according to the data set, establishing a hot-rolled bar target detection model based on a deep neural network, and training the hot-rolled bar target detection model;
acquiring real-time image data, inputting the real-time image data into a trained hot-rolled bar target detection model, and acquiring a recognition result, wherein the output result comprises information of a hot-rolled bar on an output roller way of an inspection bench;
and judging whether scattered bars exist on the output roller way of the inspection bench or not according to the identification result, and finishing the collection of the hot rolled bars and finishing the detection of the blanking of the roller way.
Optionally, the labeling the scattering rods in the image information, and acquiring the data set includes: the method comprises the steps of marking the positions of scattered bars through a rectangular selection frame of an image marking tool, further forming a data set of the scattered bars, dividing the data set into a training set, a testing set and a verification set, training a hot rolling bar target detection model through data in the training set, and obtaining the hot rolling bar target detection model through learning target features in an identification frame range in each hot rolling bar image in the training set.
Optionally, the effective information of the data set includes image basic attributes and annotation information, and the image basic attributes include file name, width, height, and image depth; the labeling information includes a category of the target object.
Optionally, inputting real-time video stream data to the trained hot-rolled bar target detection model for target identification;
and acquiring the position information of the scattered bars on the roller way, wherein the position information of the scattered bars on the roller way comprises upper left, lower right and upper right points of the rectangular target frame and coordinate information of the upper left, lower right and upper right points.
And acquiring real-time position information and historical position information of the target bar, and judging the motion state of the target bar according to the real-time position information and the historical position information.
Optionally, the real-time location information includes:
[Bar Point1(x1,y1),Bar Point2(x1,y1),Bar Point3(x1,y1),Bar Point4(x1,y1)]
the historical location information includes:
[Bar Point1(x2,y2),Bar Point2(x2,y2),Bar Point3(x2,y2),Bar Point4(x2,y2)]
wherein Bar Point1x1、Bar Point1y1Respectively representing x and y coordinates of the upper left corner of the target identification box of the current detection time node;
Bar Point4x1、Bar Point4y1the x and y coordinates of the lower right corner of the target identification frame of the current detection time node are respectively;
Bar Point1x2、Bar Point1y2x and y coordinates of the upper left corner of the target identification box of the previous detection time node respectively;
Bar Point4x2、Bar Point4y2and the x and y coordinates of the lower right corner of the target identification box of the last detection time node are respectively.
Optionally, the variation between the target identification frame of the current detection time node and the target identification frame of the previous detection time node is calculated according to the real-time position information and the historical position information, whether the target bar is stacked on the roller way and is still is judged according to the variation, and then whether the target bar is in a still state is judged.
Optionally, whether the target bar is in a static state is judged by the following judgment conditions:
|Bar Point1x1-Bar Point1x2|<Dx
|Bar Point1y1-Bar Point1y2|<Dy
wherein | Bar Point1x1-Bar Point1x2| is the absolute value of the difference value between the x coordinate of the upper left corner of the target recognition frame of the current detection time node and the x coordinate of the upper left corner of the target recognition frame of the previous detection time node, | Bar Point1y1-Bar Point1y2I is the y coordinate of the upper left corner of the target identification frame of the current detection time node and the target identification frame of the previous detection time nodeAbsolute value of the difference in y-coordinate of the upper left corner, DxIs a preset first variation threshold value, DyThe second variable quantity threshold is preset;
and continuously judging the n graphs, and when the judgment conditions are met, judging that the target bar is in a static state, and finishing the judgment of the scattering state of the target bar.
Optionally, when the target hot-rolled bar is in a static state, whether scattered bars exist on the roller way or not is judged, and then an abnormal signal is fed back and an alarm is given.
The invention also provides a hot-rolled bar fixed support separation detection system, which comprises:
the image acquisition module is used for acquiring image information of a roller way after the hot rolled bar is collected;
the image processing module is used for checking the position of a table output roller way in the image information, setting an interested area, labeling scattered bars in the image information and acquiring a data set;
the detection model is used for establishing a hot-rolled bar target detection model based on a deep neural network according to the data set and training the hot-rolled bar target detection model;
acquiring real-time image data, inputting the real-time image data into a trained hot-rolled bar target detection model, and acquiring a recognition result, wherein the output result comprises information of a hot-rolled bar on an output roller way of an inspection bench;
and judging whether scattered bars exist on the output roller way of the inspection bench or not according to the identification result, and finishing the collection of the hot rolled bars and finishing the detection of the blanking of the roller way.
The invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any one of the above.
The present invention also provides an electronic terminal, comprising: a processor and a memory;
the memory is adapted to store a computer program and the processor is adapted to execute the computer program stored by the memory to cause the terminal to perform the method as defined in any one of the above.
The invention has the beneficial effects that: according to the method, the system, the medium and the terminal for detecting the hot rolled bar collecting and finishing roller way blanking, the neural network and the deep learning are utilized, the scattering condition of the hot rolled bar in a picture can be identified in real time, the scattering bar on the rack roller way is detected in real time, and the warning signal is returned when the scattering bar is detected to remind an operator to process, so that the conditions of missing detection and error detection caused by manual identification are avoided, and the safety and the accuracy of detecting the hot rolled bar collecting and finishing roller way blanking are improved.
Drawings
FIG. 1 is a schematic overall flow chart of a roller way blanking detection method for completing collection of hot rolled bars in the embodiment of the invention.
FIG. 2 is a schematic view of a specific detection flow of the roller way blanking detection method for completing the collection of the hot rolled bars in the embodiment of the invention.
FIG. 3 is a schematic diagram of bar images collected by a camera of the method for detecting the hot rolled bar after the hot rolled bar is collected and rolled on the roller way.
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 is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments 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.
In the following description, numerous details are set forth to provide a more thorough explanation of embodiments of the present invention, however, it will be apparent to one skilled in the art that embodiments of the present invention may be practiced without these specific details, and in other embodiments, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring embodiments of the present invention.
As shown in fig. 1, the method for detecting the blanking of the roller way after the collection of the hot rolled bars in the embodiment includes:
acquiring image information of a roller way for collecting hot-rolled bars;
checking the position of a table frame output roller way according to the image information, and setting an interested area;
labeling scattered bars in the image information to obtain a data set;
according to the data set, establishing a hot-rolled bar target detection model based on a deep neural network, and training the hot-rolled bar target detection model;
acquiring real-time image data, inputting the real-time image data into a trained hot-rolled bar target detection model, and acquiring a recognition result, wherein the output result comprises information of a hot-rolled bar on an output roller way of an inspection bench;
and judging whether scattered bars exist on the output roller way of the inspection bench or not according to the identification result, and finishing the collection of the hot rolled bars and finishing the detection of the blanking of the roller way.
In this embodiment, as shown in fig. 2, a monitoring camera needs to be installed in an actual industrial scene, the camera is used to collect an image of a hot rolled bar sample, and the camera is installed above an output roller way of an inspection bench in a finishing area. And then labeling the condition of scattering the bars in the image sample data. Carrying out image annotation on a hot-rolled bar picture shot and obtained in a specific industrial scene, marking the position of a scattered bar by using a rectangular selection frame of an image annotation tool, making a scattered bar data set, and dividing the scattered bar data set into three parts: training set, testing set, and verifying set, training the scattered bar target detection model by using the data of the training set. Effective information which can be used for training in the hot rolled bar training set after image labeling comprises image basic attributes and labeling information. The picture basic attributes are: filename-filename, width-width, height-height, depth-image depth. The labeling information includes: class, i.e. whether there are stray bars. And then, establishing a hot-rolled bar target detection model based on the deep neural network, inputting the collected sample image data for training, and obtaining the hot-rolled bar target detection model based on the deep neural network. And finally obtaining a hot rolling bar target detection model by learning the target characteristics within the range of the identification frame in each hot rolling bar training set image. Optionally, the neural network in this embodiment adopts an SSD-MobileNet neural network, and those skilled in the art may implement the similar effect to this embodiment by using a straight line or other target recognition neural networks, such as R-CNN, Faster-RCNN and YOLO series, and the details are not repeated herein.
In this embodiment, a real-time image is collected and input into a deep neural network-based hot rolled bar target detection model, so as to obtain information of a hot rolled bar on an output roller way of an inspection bench. All the information of the scattered bars in the input image can be obtained through the hot rolling bar target detection model. And inputting the acquired real-time image data into a hot-rolled bar target detection model, and outputting the model to obtain the position information of the scattered bars on the roller way. The format and content of the output position information are as follows:
[Bar Point1,Bar Point2,Bar Point3,Bar Point4]
the four coordinates in the list correspond to the upper left, lower right, and upper right points of the rectangular target frame, respectively.
[Bar Point1(x,y),Bar Point2(x,y),Bar Point3(x,y),Bar Point4(x,y)]Respectively represent the horizontal and vertical coordinates of the upper left point, the lower right point and the upper right point.
The real-time location information includes:
[Bar Point1(x1,y1),Bar Point2(x1,y1),Bar Point3(x1,y1),Bar Point4(x1,y1)]
the historical location information includes:
[Bar Point1(x2,y2),Bar Point2(x2,y2),Bar Point3(x2,y2),Bar Point4(x2,y2)]
wherein Bar Point1x1、Bar Point1y1Respectively representing x and y coordinates of the upper left corner of the target identification box of the current detection time node;
Bar Point4x1、Bar Point4y1the x and y coordinates of the lower right corner of the target identification frame of the current detection time node are respectively;
Bar Point1x2、Bar Point1y2x and y coordinates of the upper left corner of the target identification box of the previous detection time node respectively;
Bar Point4x2、Bar Point4y2and the x and y coordinates of the lower right corner of the target identification box of the last detection time node are respectively.
And judging whether scattered bars exist on the output roller way of the inspection bench or not, and feeding back a judgment result.
Judging the motion state of a target bar, wherein the judgment mode of the motion state of the target bar is as follows:
calculating the variation between the target identification frame of the current detection time node and the target identification frame of the previous detection time node according to the real-time position information and the historical position information, judging whether the target bar is stacked on the roller way statically according to the variation, and mathematically expressing whether the target bar is in a static state:
|Bar Point1x1-Bar Point1x2|<Dx
|Bar Point1y1-Bar Point1y2|<Dy
wherein | Bar Point1x1-Bar Point1x2| is the absolute value of the difference value between the x coordinate of the upper left corner of the target recognition frame of the current detection time node and the x coordinate of the upper left corner of the target recognition frame of the previous detection time node, | Bar Point1y1-Bar Point1y2I is the absolute value of the difference value of the y coordinate of the upper left corner of the target identification frame of the current detection time node and the y coordinate of the upper left corner of the target identification frame of the previous detection time node, DxIs a preset first variation threshold value, DyIs a preset second variation threshold；
And continuously judging the n graphs, and when the mathematical expressions are simultaneously met, judging that the target bar is in a static state, namely clamped on the roller way, and finishing the judgment of the scattering state of the target bar.
And judging whether scattered bars exist on the roller way or not through a deep learning algorithm. If the scattered bar exists, an abnormal signal is fed back; and if the scattering bars do not exist, feeding back a normal signal.
In this embodiment, when the target of the hot-rolled bar is in a static state, that is, when the target is clamped on the roller way, an alarm can be given through sound and light alarms, and an abnormal signal is output to remind workers of handling. Similar effects can be achieved for other abnormal feedback situations, such as by transmitting an abnormal signal to the system, which controls and handles the situation.
Correspondingly, the present embodiment further provides a hot-rolled bar fixed support separation detection system, including:
the image acquisition module is used for acquiring image information of a roller way after the hot rolled bar is collected;
the image processing module is used for checking the position of a table output roller way in the image information, setting an interested area, labeling scattered bars in the image information and acquiring a data set;
the detection model is used for establishing a hot-rolled bar target detection model based on a deep neural network according to the data set and training the hot-rolled bar target detection model;
acquiring real-time image data, inputting the real-time image data into a trained hot-rolled bar target detection model, and acquiring a recognition result, wherein the output result comprises information of a hot-rolled bar on an output roller way of an inspection bench;
and judging whether scattered bars exist on the output roller way of the inspection bench or not according to the identification result, and finishing the collection of the hot rolled bars and finishing the detection of the blanking of the roller way.
In this embodiment, the hot-rolled bar fixed-support separation detection system performs fixed-support separation detection on the hot-rolled bar by using the hot-rolled bar target detection model through the above method.
The present embodiment also provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements any of the methods in the present embodiments.
The present embodiment further provides an electronic terminal, including: a processor and a memory;
the memory is used for storing computer programs, and the processor is used for executing the computer programs stored by the memory so as to enable the terminal to execute the method in the embodiment.
The computer-readable storage medium in the present embodiment can be understood by those skilled in the art as follows: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The electronic terminal provided by the embodiment comprises a processor, a memory, a transceiver and a communication interface, wherein the memory and the communication interface are connected with the processor and the transceiver and are used for completing mutual communication, the memory is used for storing a computer program, the communication interface is used for carrying out communication, and the processor and the transceiver are used for operating the computer program so that the electronic terminal can execute the steps of the method.
In this embodiment, the Memory may include a Random Access Memory (RAM), and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In the above embodiments, unless otherwise specified, the description of common objects by using "first", "second", etc. ordinal numbers only indicate that they refer to different instances of the same object, rather than indicating that the objects being described must be in a given sequence, whether temporally, spatially, in ranking, or in any other manner.
In the above-described embodiments, reference in the specification to "the present embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least some embodiments, but not necessarily all embodiments. The multiple occurrences of "the present embodiment" do not necessarily all refer to the same embodiment.
In the embodiments described above, although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory structures (e.g., dynamic ram (dram)) may use the discussed embodiments. The embodiments of the invention are intended to embrace all such alternatives, modifications and variances that fall within the broad scope of the appended claims.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
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.
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 of the present invention and its efficacy, and are not to be construed as limiting 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 (11)
1. A hot rolled bar collecting and finishing roller way blanking detection method is characterized by comprising the following steps:
acquiring image information of a roller way for collecting hot-rolled bars;
checking the position of a table frame output roller way according to the image information, and setting an interested area;
labeling scattered bars in the image information to obtain a data set;
according to the data set, establishing a hot-rolled bar target detection model based on a deep neural network, and training the hot-rolled bar target detection model;
acquiring real-time image data, inputting the real-time image data into a trained hot-rolled bar target detection model, and acquiring a recognition result, wherein the output result comprises information of a hot-rolled bar on an output roller way of an inspection bench;
and judging whether scattered bars exist on the output roller way of the inspection bench or not according to the identification result, and finishing the collection of the hot rolled bars and finishing the detection of the blanking of the roller way.
2. The hot rolled bar collecting and completing roller way blanking detection method according to claim 1, wherein the labeling of the scattered bars in the image information and the obtaining of the data set comprise: the method comprises the steps of marking the positions of scattered bars through a rectangular selection frame of an image marking tool, further forming a data set of the scattered bars, dividing the data set into a training set, a testing set and a verification set, training a hot rolling bar target detection model through data in the training set, and obtaining the hot rolling bar target detection model through learning target features in an identification frame range in each hot rolling bar image in the training set.
3. The hot rolled bar collecting and completing roller bed blanking detection method according to claim 1, wherein the effective information of the data set includes image basic attributes and labeling information, and the image basic attributes include file name, width, height, and image depth; the labeling information includes a category of the target object.
4. The hot rolled bar collecting and finishing roller way blanking detection method according to claim 2,
inputting real-time video stream data to a trained hot-rolled bar target detection model for target identification;
and acquiring the position information of the scattered bars on the roller way, wherein the position information of the scattered bars on the roller way comprises upper left, lower right and upper right points of the rectangular target frame and coordinate information of the upper left, lower right and upper right points.
And acquiring real-time position information and historical position information of the target bar, and judging the motion state of the target bar according to the real-time position information and the historical position information.
5. The hot rolled bar collecting and finishing roller way blanking detection method according to claim 4,
the real-time location information includes:
[Bar Point1(x1,y1),Bar Point2(x1,y1),Bar Point3(x1,y1),Bar Point4(x1,y1)]
the historical location information includes:
[Bar Point1(x2,y2),Bar Point2(x2,y2),Bar Point3(x2,y2),Bar Point4(x2,y2)]
wherein Bar Point1x1、Bar Point1y1Respectively representing x and y coordinates of the upper left corner of the target identification box of the current detection time node;
Bar Point4x1、Bar Point4y1the x and y coordinates of the lower right corner of the target identification frame of the current detection time node are respectively;
Bar Point1x2、Bar Point1y2x and y coordinates of the upper left corner of the target identification box of the previous detection time node respectively;
Bar Point4x2、Bar Point4y2and the x and y coordinates of the lower right corner of the target identification box of the last detection time node are respectively.
6. The hot rolled bar collecting and finishing roller way blanking detection method according to claim 5, wherein a variation between a target identification frame of a current detection time node and a target identification frame of a previous detection time node is calculated according to the real-time position information and the historical position information, and whether a target bar is stacked on a roller way and is stationary is judged according to the variation, and whether the target bar is stationary is further judged.
7. The hot rolled bar collecting and finishing roller way blanking detection method according to claim 6, characterized in that whether the target bar is in a static state is judged by the following judgment conditions:
|Bar Point1x1-Bar Point1x2|<Dx
|Bar Point1y1-Bar Point1y2|<Dy
wherein | Bar Point1x1-Bar Point1x2' left upper corner of target identification box with current detection time node |Is compared with the absolute value of the difference between the x coordinate of the upper left corner of the target recognition box of the last detection time node, | Bar Point1y1-Bar Point1y2I is the absolute value of the difference value of the y coordinate of the upper left corner of the target identification frame of the current detection time node and the y coordinate of the upper left corner of the target identification frame of the previous detection time node, DxIs a preset first variation threshold value, DyThe second variable quantity threshold is preset;
and continuously judging the n graphs, and when the judgment conditions are met, judging that the target bar is in a static state, and finishing the judgment of the scattering state of the target bar.
8. The method for detecting the hot rolled bar collecting and finishing roller way blanking according to any one of claims 1 to 7, wherein when the target hot rolled bar is in a static state, whether scattered bars exist on the roller way or not is judged, and an abnormal signal is fed back and an alarm is given.
9. A hot rolled bar fixed support separation detection system is characterized by comprising:
the image acquisition module is used for acquiring image information of a roller way after the hot rolled bar is collected;
the image processing module is used for checking the position of a table output roller way in the image information, setting an interested area, labeling scattered bars in the image information and acquiring a data set;
the detection model is used for establishing a hot-rolled bar target detection model based on a deep neural network according to the data set and training the hot-rolled bar target detection model;
acquiring real-time image data, inputting the real-time image data into a trained hot-rolled bar target detection model, and acquiring a recognition result, wherein the output result comprises information of a hot-rolled bar on an output roller way of an inspection bench;
and judging whether scattered bars exist on the output roller way of the inspection bench or not according to the identification result, and finishing the collection of the hot rolled bars and finishing the detection of the blanking of the roller way.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when executed by a processor, implements the method of any one of claims 1 to 9.
11. An electronic terminal, comprising: a processor and a memory;
the memory is for storing a computer program and the processor is for executing the computer program stored by the memory to cause the terminal to perform the method of any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010896107.4A CN112037199A (en) | 2020-08-31 | 2020-08-31 | Hot rolled bar collecting and finishing roller way blanking detection method, system, medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010896107.4A CN112037199A (en) | 2020-08-31 | 2020-08-31 | Hot rolled bar collecting and finishing roller way blanking detection method, system, medium and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112037199A true CN112037199A (en) | 2020-12-04 |
Family
ID=73585919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010896107.4A Pending CN112037199A (en) | 2020-08-31 | 2020-08-31 | Hot rolled bar collecting and finishing roller way blanking detection method, system, medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112037199A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112749735A (en) * | 2020-12-30 | 2021-05-04 | 中冶赛迪重庆信息技术有限公司 | Converter tapping steel flow identification method, system, medium and terminal based on deep learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490842A (en) * | 2019-07-22 | 2019-11-22 | 同济大学 | A kind of steel strip surface defect detection method based on deep learning |
| CN110992325A (en) * | 2019-11-27 | 2020-04-10 | 同济大学 | Target counting method, device and equipment based on deep learning |
| CN111429425A (en) * | 2020-03-20 | 2020-07-17 | 中冶赛迪重庆信息技术有限公司 | Rolling mill inlet abnormity identification method based on deep learning |
| CN111429424A (en) * | 2020-03-20 | 2020-07-17 | 中冶赛迪重庆信息技术有限公司 | Heating furnace inlet abnormity identification method based on deep learning |
-
2020
- 2020-08-31 CN CN202010896107.4A patent/CN112037199A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490842A (en) * | 2019-07-22 | 2019-11-22 | 同济大学 | A kind of steel strip surface defect detection method based on deep learning |
| CN110992325A (en) * | 2019-11-27 | 2020-04-10 | 同济大学 | Target counting method, device and equipment based on deep learning |
| CN111429425A (en) * | 2020-03-20 | 2020-07-17 | 中冶赛迪重庆信息技术有限公司 | Rolling mill inlet abnormity identification method based on deep learning |
| CN111429424A (en) * | 2020-03-20 | 2020-07-17 | 中冶赛迪重庆信息技术有限公司 | Heating furnace inlet abnormity identification method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 成鹏飞等: "基于机器视觉的钢棒自动计数系统", 《冶金自动化》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112749735A (en) * | 2020-12-30 | 2021-05-04 | 中冶赛迪重庆信息技术有限公司 | Converter tapping steel flow identification method, system, medium and terminal based on deep learning |
| CN112749735B (en) * | 2020-12-30 | 2023-04-07 | 中冶赛迪信息技术(重庆)有限公司 | Converter tapping steel flow identification method, system, medium and terminal based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108009515B (en) | Power transmission line positioning and identifying method of unmanned aerial vehicle aerial image based on FCN | |
| US20160253618A1 (en) | Method and apparatus for work quality control | |
| US11763463B2 (en) | Information processing apparatus, control method, and program | |
| CN112348791B (en) | Intelligent scrap steel detecting and judging method, system, medium and terminal based on machine vision | |
| JP2015041164A (en) | Image processor, image processing method and program | |
| CN113378952A (en) | Method, system, medium and terminal for detecting deviation of belt conveyor | |
| CN111429424B (en) | Heating furnace inlet anomaly identification method based on deep learning | |
| CN113012157B (en) | Visual detection method and system for equipment defects | |
| CN113255626B (en) | Intelligent tower crane structure state detection method and device based on scanned image analysis | |
| CN117671607B (en) | Real-time detection method and system for abnormality of belt conveyor based on computer vision | |
| CN112766045A (en) | Scene change detection method, system, electronic device and storage medium | |
| CN112053333A (en) | Square billet detection method, system, equipment and medium based on machine vision | |
| CN116593479B (en) | Method, device, equipment and storage medium for detecting appearance quality of battery cover plate | |
| CN112037198B (en) | Hot-rolled bar fixed support separation detection method, system, medium and terminal | |
| US20230033875A1 (en) | Image recognition method, image recognition apparatus and computer-readable non-transitory recording medium storing image recognition program | |
| CN112037199A (en) | Hot rolled bar collecting and finishing roller way blanking detection method, system, medium and terminal | |
| CN112053336B (en) | Bar alignment detection method, system, equipment and medium | |
| CN112053339B (en) | Rod finished product warehouse driving safety monitoring method, device and equipment based on machine vision | |
| CN111968103B (en) | Steel coil interval detection method, system, medium and electronic terminal | |
| CN111968104B (en) | Machine vision-based steel coil abnormity identification method, system, equipment and medium | |
| CN113177941A (en) | Steel coil edge crack identification method, system, medium and terminal | |
| CN112308848A (en) | Method and system for identifying state of baffle plate of scrap steel truck, electronic equipment and medium | |
| CN111860035A (en) | Book cover detection method and device, storage medium and electronic equipment | |
| CN112037195B (en) | Method, system, equipment and medium for detecting abnormal length of bar | |
| CN114463690A (en) | Abnormity detection method and device, electronic 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 | ||
| 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. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201204 |