Method and device for monitoring a bar shearing device

Abstract

The application discloses a kind of bar shearing device monitoring method and device, the method includes: the process image of the head section and tail section of target bar that target bar is obtained by bar shearing device shearing obtains the sliding process;Determine the head section tail section area in each frame image;For each frame image, determine first sub-region and second sub-region;Add multiple division lines to the minimum circumscribed rectangle of second sub-region;The maximum number of intersection of different division lines and the second sub-region is as the number of bar containing head and tail section in second sub-region;The sum of the number of first sub-region and the number of second sub-region is determined as the target quantity of head section and tail section of target bar under the frame image;Determine the maximum value in the target quantity of each frame image;When the maximum value is different from the set shearing section number of bar shearing device, send alarm information.The application is used to improve the efficiency and accuracy of bar shearing device monitoring, reduce the monitoring cost of bar shearing device.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to a monitoring method and device for a bar shearing device. BACKGROUND

[0002] This section is intended to provide background or context to the embodiments of the application recited in the claims. The description herein does not constitute admission that the subject matter disclosed herein is prior art to the present application.

[0003] A bar shearing device, such as a high-speed bar shearing device, is installed before a finishing rolling mill group to cut the head and tail of the bar during the rolling process, and to break the bar. The head and tail are cut to ensure that the high-speed rolled bar can smoothly enter the downstream rolling mill, and the size accuracy and quality after rolling can meet the production requirements. The high-speed shearing device is continuously operated by a servo motor. When the bar reaches the shearing blade, the irregular length of the head of the bar is continuously sheared according to the set strategy. Several head sections (usually 3 sections) can be cut off, and the cut-off head sections will fall into the waste hopper under the production platform. Similarly, when the bar is about to leave the shearing blade, the irregular length of the tail of the bar is continuously sheared according to the set strategy. Several tail sections (usually 3 sections) can also be cut off, and the cut-off tail sections will also fall into the waste hopper (as shown in Figure 1

[0004] All the head sections and tail sections sheared by the high-speed shearing device must fall onto the waste hopper under the platform along the side slide of the material falling chute, as shown in Figure 1 If the head section enters the rolling mill roll way, it will cause the steel stacking accident of the current bar, and if the tail section enters the rolling mill roll way, it will cause the steel stacking accident of the next bar. Therefore, the entry of the head section or the tail section into the rolling mill roll way will cause the steel stacking accident and stop the machine, which should be avoided. In normal production, a full-time worker is usually arranged to manually count the number of the cut-off head sections and tail sections falling into the waste hopper under the platform. If the number of the falling sections is found to be different from the set number of the high-speed shearing device, the main operator is immediately notified to stop the steel discharge, and the on-site inspection is carried out. After confirmation, the production can continue. However, this counting method relying on a full-time worker is not only a waste of labor (the manual counting is boring, mechanical, and the working link is harsh), but also cannot guarantee the long-term accuracy and real-time of the counting, which is contrary to the current industrial development trend of reducing the number of employees and increasing efficiency and intelligent production. SUMMARY

[0005] The embodiments of the present application provide a monitoring method for a bar shearing device to improve the efficiency and accuracy of the monitoring of the bar shearing device and reduce the monitoring cost of the bar shearing device. The method comprises:

[0006] ​Process images of a sliding process of head sections and tail sections of a target bar obtained by a bar shearing device are acquired; the head sections and the tail sections enter a waste hopper through a sliding channel;

[0007] Head section and tail section areas in each frame of the process images are determined according to pixel distribution values of each frame of the process images and background pixel distribution values of the sliding channel; pixel values of the head section and tail section areas are greater than area pixel values of corresponding head section and tail section areas in the background pixel distribution values;

[0008] For each frame of the images, connected domain analysis is performed on the head section and tail section areas in the frame of the images to determine a plurality of sub-areas of the head section and tail section areas;

[0009] For each sub-area of each frame of the images, a rectangular degree of each sub-area is determined; the rectangular degree is used to describe a ratio between an area of the sub-area and an area of a minimum circumscribed rectangle of the sub-area;

[0010] A sub-area with a rectangular degree greater than or equal to a preset value is regarded as a first sub-area; a sub-area with a rectangular degree less than the preset value is regarded as a second sub-area; a plurality of division lines are added to the minimum circumscribed rectangle of the second sub-area; a maximum number of intersections of different division lines and the second sub-area is regarded as a number of head section and tail section-containing strips in the second sub-area;

[0011] A sum of a number of the first sub-areas and the number of the strips of the second sub-areas is determined as a target number of the head sections and the tail sections of the target bar in the frame of the images;

[0012] A maximum value in the target number of each frame of the images is determined; when the maximum value is different from a set shearing section number of the bar shearing device, an alarm information is sent.

[0013] Embodiments of the present application also provide a monitoring device of a bar shearing device to improve efficiency and accuracy of monitoring of the bar shearing device and reduce monitoring cost of the bar shearing device; the device comprises:

[0014] A process image acquisition module is configured to acquire process images of a sliding process of head sections and tail sections of a target bar obtained by a bar shearing device; the head sections and the tail sections enter a waste hopper through a sliding channel;

[0015] A head section and tail section area determination module is configured to determine head section and tail section areas in each frame of the process images according to pixel distribution values of each frame of the process images and background pixel distribution values of the sliding channel; pixel values of the head section and tail section areas are greater than area pixel values of corresponding head section and tail section areas in the background pixel distribution values;

[0016] A sub-area determination module is configured to perform connected domain analysis on the head section and tail section areas in each frame of the images to determine a plurality of sub-areas of the head section and tail section areas for each frame of the images.

[0017] a rectangularity determining module configured to determine a rectangularity of each sub-region for each sub-region of each frame of image; the rectangularity is used to describe a ratio between an area of the sub-region and an area of a minimum circumscribed rectangle of the sub-region;

[0018] a sub-region head-tail segment number determining module configured to take a sub-region with a rectangularity greater than or equal to a preset value as a first sub-region; take a sub-region with a rectangularity less than the preset value as a second sub-region; add a plurality of segmentation lines to the minimum circumscribed rectangle of the second sub-region; and take a maximum number of intersections of different segmentation lines and the second sub-region as a number of head-tail segments contained in the second sub-region;

[0019] a head-tail segment number determining module configured to determine a target number of head segments and tail segments of a target bar in the frame of image as a sum of a number of the first sub-regions and the number of the second sub-region;

[0020] an alarm module configured to determine a maximum value in the target number of each frame of image; and send an alarm information when the maximum value is different from a set number of sheared segments of the bar shearing device.

[0021] The embodiment of the present application further provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the processor implements the monitoring method of the bar shearing device when executing the computer program.

[0022] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program implements the monitoring method of the bar shearing device when executed by a processor.

[0023] The embodiment of the present application further provides a computer program product, which comprises a computer program, and the computer program implements the monitoring method of the bar shearing device when executed by a processor.

[0024] In the embodiment of the present application, the process images of the sliding process of the head section and the tail section obtained by the bar shearing device are acquired; the head section and the tail section enter the waste hopper through the sliding channel; the head section and the tail section area in each frame of image is determined according to the pixel distribution value of each frame of image and the background pixel distribution value of the sliding channel; the pixel value of the head section and the tail section area is greater than the area pixel value of the corresponding head section and tail section area in the background pixel distribution value; for each frame of image, the connected domain analysis is performed on the head section and tail section area in the frame of image to determine a plurality of sub-areas of the head section and tail section area; for each sub-area of each frame of image, the rectangularity of each sub-area is determined; the rectangularity is used to describe the ratio between the area of the sub-area and the minimum circumscribed rectangle area of the sub-area; the sub-area with the rectangularity greater than or equal to the preset value is taken as the first sub-area; the sub-area with the rectangularity less than the preset value is taken as the second sub-area; a plurality of division lines are added to the minimum circumscribed rectangle of the second sub-area; the maximum number of intersections of different division lines and the second sub-area is taken as the number of head section and tail section contained in the second sub-area; the sum of the number of first sub-areas and the number of second sub-areas is determined as the target number of the head section and the tail section of the target bar in the frame of image; the maximum value in the target number of each frame of image is determined; when the maximum value is different from the set shearing section number of the bar shearing device, an alarm information is sent; compared with the prior art of manually checking the shearing number of the head section and the tail section of the bar, the number of the sliding head section and tail section can be automatically determined and it is judged whether the number is consistent with the set shearing section number, so that it can be predicted whether the head section and the tail section enter the rolling mill, and real-time alarm can be made, which can assist the operator to avoid the steel stacking accident of the subsequent rolling piece, and has good practical application value. At the same time, the present application can replace the full-time counting post worker, realize the reduction of staff and increase of efficiency, improve the efficiency and accuracy of the monitoring of the bar shearing device, and reduce the monitoring cost of the bar shearing device. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort. In the drawings:

[0026] Figure 1 It is a schematic diagram of high-speed shearing of a bar shearing device in the embodiment of the present application;

[0027] Figure 2 It is a specific example diagram of installation of a vision system in the embodiment of the present application;

[0028] Figure 3This is a specific example image frame of a head-to-tail sliding process in an embodiment of the present invention;

[0029] Figure 4 This is a schematic diagram of a monitoring method for a bar shearing device in an embodiment of the present invention;

[0030] Figure 5 This is a specific example of an environmental background image after filtering, as described in an embodiment of the present invention.

[0031] Figure 6 This is a specific schematic diagram of a filtered image of a certain frame of a sliding image at the beginning and end, according to an embodiment of the present invention.

[0032] Figure 7 This is a specific example diagram of a head and tail segment region in an embodiment of the present invention;

[0033] Figure 8 This is a specific example diagram of a connected domain containing only the head and tail segments in an embodiment of the present invention;

[0034] Figure 9 This is a specific example diagram of the outer rectangle of a sub-region in an embodiment of the present invention;

[0035] Figure 10 This is a specific example diagram illustrating the process of dividing a sub-region using diagonal dividing auxiliary lines in an embodiment of the present invention;

[0036] Figure 11 This is a specific example diagram of the intersection of a diagonal segmentation auxiliary line and a sub-region in an embodiment of the present invention;

[0037] Figure 12 This is a specific example diagram illustrating the process of dividing a sub-region using parallel dividing auxiliary lines in an embodiment of the present invention;

[0038] Figure 13 This is a specific example diagram of the intersection of a parallel dividing auxiliary line and a sub-region in an embodiment of the present invention;

[0039] Figure 14 This is a flowchart illustrating a monitoring method for a bar shearing device according to an embodiment of the present invention.

[0040] Figure 15 This is a schematic diagram of the structure of a monitoring device for a bar shearing apparatus according to an embodiment of the present invention;

[0041] Figure 16 This is a schematic diagram of a computer device used for monitoring a bar shearing device in an embodiment of the present invention. Detailed Implementation

[0042] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, further detailed description will be made to the embodiments of the present application with reference to the drawings. Herein, the illustrative embodiments of the present application and the description thereof are used to explain the present application but not to limit the present application.

[0043] The term "and / or", merely describes an associated relationship, which means that there can be three relationships, for example, A and / or B, which can mean that A exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, at least one of A, B and C includes any one or more elements selected from the set consisting of A, B and C.

[0044] In the description of the present application, "comprising", "including", "having", "containing" and the like are open-ended terms that mean including but not limited to. The description of the terms "one embodiment", "one specific embodiment", "some embodiments", "for example" and the like means that the specific features, structures or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present application, the illustrative description of the above terms does not necessarily mean the same embodiment or example. Moreover, the specific features, structures or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. The order of the steps involved in the embodiments is used to illustrate the embodiments of the present application, and the order of the steps is not limited, and can be appropriately adjusted as needed.

[0045] In the technical solutions of the present application, the acquisition, storage, use, processing and the like of data comply with the relevant provisions of the relevant laws and regulations.

[0046] A bar shearing device, such as a high-speed bar shear, is installed before the finishing mill train to cut the head, tail and broken pieces of the bar during the rolling process. The head and tail are cut to ensure that the high-speed rolled bar can smoothly enter the downstream rolling mill, and the size accuracy and quality after rolling can meet the production requirements. The high-speed shear is continuously operated by a servo motor. When the bar runs to the shear blade, the irregular length of the head of the bar is continuously sheared according to the set strategy, and several (usually 3) head sections can be cut off. The cut-off head sections will fall into the waste hopper under the production platform. Figure 1

[0047] All the head sections and tail sections sheared by the high-speed shear must be dropped into the waste hopper under the platform along the side slide of the drop chute, as shown in​Figure 1 As shown, if a cut-off section enters the rolling mill table, it will cause a steel pile-up accident on the current bar; if a cut-off section enters the rolling mill table, it will cause a steel pile-up accident on the next bar. Therefore, both cut-off and cut-off sections entering the rolling mill table will cause steel pile-up accidents and shutdowns, which must be avoided at all costs. During normal production, a dedicated worker is usually assigned to manually count the cut-off and cut-off sections falling from the scrap hopper below the platform. If the number of fallen sections is found to be inconsistent with the high-speed shear's set number, the main operator is immediately notified to stop steel output and conduct an on-site inspection. Production can only continue after confirmation. However, this method of relying on a dedicated worker for counting is wasteful of manpower (manual counting is tedious, mechanical, and involves harsh working conditions), cannot guarantee long-term accuracy and real-time performance, and goes against the current industrial development trend of reducing manpower, increasing efficiency, and intelligent manufacturing.

[0048] For example, currently, counting relies heavily on workers on-site or on video monitors in the control room to observe the material falling from the beginning and end of the shear. If the number of falling segments is inconsistent with the set number of segments for the high-speed shear, the main operator is notified to stop steel production and conduct an on-site inspection. Production can only continue after confirmation. However, these methods rely entirely on manual counting, which is not only physically demanding and exposes workers to harsh working conditions, but also cannot guarantee the real-time and long-term accuracy of the counting. This counting method is unfriendly to both personnel and production, and goes against the current industrial development trend of reducing manpower, increasing efficiency, and intelligent manufacturing.

[0049] To address the aforementioned problems, embodiments of the present invention provide a monitoring method for a bar shearing device, thereby improving the efficiency and accuracy of monitoring the bar shearing device and reducing its monitoring costs. (See also...) Figure 14 The method may include:

[0050] Step 1401: Obtain process images of the head and tail sections of the target bar being sheared by the bar shearing device and then sliding down; the head and tail sections enter the waste hopper through the sliding channel;

[0051] Step 1402: Based on the pixel distribution values ​​of each frame in the process image and the background pixel distribution values ​​of the sliding channel, determine the head and tail regions in each frame; the pixel values ​​of the head and tail regions are greater than the corresponding region pixel values ​​in the background pixel distribution values.

[0052] Step 1403: For each frame of image, perform connected component analysis on the head and tail regions of the frame to determine multiple sub-regions of the head and tail regions;

[0053] Step 1404: determining a rectangularity of each sub-region for each sub-region; the rectangularity is used to describe a ratio between an area of the sub-region and an area of a minimum circumscribed rectangle of the sub-region;

[0054] Step 1405: taking a sub-region with a rectangularity greater than or equal to a preset value as a first sub-region; taking a sub-region with a rectangularity less than the preset value as a second sub-region; adding a plurality of split lines to the minimum circumscribed rectangle of the second sub-region; taking a maximum number of intersections of different split lines with the second sub-region as a number of head-tail sections contained in the second sub-region;

[0055] Step 1406: determining a sum of a number of the first sub-regions and the number of the second sub-regions as a target number of head sections and tail sections of the target rod in the frame image;

[0056] Step 1407: issuing an alarm information when the target number is not equal to a set number of cut sections of a rod cutting device.

[0057] In the embodiment of the application, process images of the sliding process of the head section and the tail section obtained by the target bar being cut by the bar cutting device are acquired; the head section and the tail section enter the waste hopper through the sliding channel; the head section and the tail section area in each frame of image is determined according to the pixel distribution value of each frame of image in the process image and the background pixel distribution value of the sliding channel; the pixel value of the head section and the tail section area is greater than the area pixel value of the corresponding head section and tail section area in the background pixel distribution value; for each frame of image, the head section and tail section area in the frame of image is subjected to connected domain analysis to determine a plurality of sub-areas of the head section and tail section area; for each sub-area of each frame of image, the rectangularity of each sub-area is determined; the rectangularity is used to describe the ratio between the area of the sub-area and the minimum circumscribed rectangle area of the sub-area; the sub-area with the rectangularity greater than or equal to a preset value is taken as a first sub-area; the sub-area with the rectangularity less than the preset value is taken as a second sub-area; a plurality of division lines are added to the minimum circumscribed rectangle of the second sub-area; the maximum number of intersections of different division lines and the second sub-area is taken as the number of head section and tail section contained in the second sub-area; the sum of the number of first sub-areas and the number of second sub-areas is determined as the target number of the head section and the tail section of the target bar in the frame of image; the maximum value in the target number of each frame of image is determined; when the maximum value is different from the set cutting section number of the bar cutting device, an alarm information is sent, compared with the technical scheme of manually checking the cutting number of the head section and the tail section of the bar in the prior art, the number of the sliding head section and tail section can be automatically determined and it is judged whether the number is consistent with the set cutting number, so that it can be predicted whether the head section and the tail section enter the rolling mill bed, and real-time alarm can be made, which can assist the operator to avoid the steel stacking accident of the subsequent rolling piece, and has good practical application value. Meanwhile, the invention can replace the full-time counting post worker, realize reduction of staff and increase of efficiency, improve the efficiency and accuracy of the monitoring of the bar cutting device, and reduce the monitoring cost of the bar cutting device.

[0058] In specific implementation, first, process images of the sliding process of the head section and the tail section obtained by the target bar being cut by the bar cutting device are acquired; the head section and the tail section enter the waste hopper through the sliding channel.

[0059] In the embodiment, one industrial camera can be installed opposite the material falling groove under the steel rolling production platform, and the field of view of the camera covers the entire side sliding way of the falling groove, so as to realize the identification of the number of high-speed cut head section and tail section.

[0060] In specific implementation, process images of the sliding process of the head section and the tail section obtained by the target bar being cut by the bar cutting device are acquired; the head section and the tail section enter the waste hopper through the sliding channel, and the head section and tail section area in each frame of image is determined according to the pixel distribution value of each frame of image in the process image and the background pixel distribution value of the sliding channel; the pixel value of the head section and the tail section area is greater than the area pixel value of the corresponding head section and tail section area in the background pixel distribution value.

[0061] In the embodiment, the method further comprises:

[0062] The process image of the target bar is acquired based on a camera arranged opposite to the drop groove under the steel rolling production platform.

[0063] In the embodiment, after the high-speed shearing starts, each frame image of the head and tail section sliding process can be acquired in real time from the camera until the sliding process of the head and tail section ends, and the given Dt value ensures that the image of the entire sliding process of the head and tail section can be acquired, for example, Dt is 20 seconds.

[0064] In one embodiment, the method further comprises:

[0065] The pixel distribution value of each frame image is determined as follows:

[0066] Each frame image is converted from a three-channel color image into a single-channel grayscale image.

[0067] A convolution operation is used to filter the single-channel grayscale image of each frame image to obtain a single-channel grayscale image after filtering.

[0068] The pixel distribution value of the single-channel grayscale image after filtering is determined.

[0069] For example, a frame of environmental background image FrameBK is acquired from the camera, which is a three-channel color image, and channel conversion is needed. Since the head and tail sections in the image are red steel, the head and tail sections have a stronger contrast with surrounding objects in the red channel image, and therefore the three-channel color image is converted into a single-channel grayscale image FrameBKS by acquiring the red channel image.

[0070] In order to eliminate the influence of noise or noise points in the background image on image recognition, the environmental background image is filtered by using a convolution operation. The parameters used in the convolution operation are as follows: the filter matrix Filter is a 5*5 unit matrix (formula 1), the sliding step Stride is 1, and the edge periphery is supplemented with 0. The inner product of the filter matrix and the image matrix (each pixel point) is obtained to obtain the filtered image FrameBKSE.

[0071] In one embodiment, according to the pixel distribution value of each frame image in the process image and the background pixel distribution value of the sliding channel, the head and tail section area in each frame image is determined, which comprises: for each area in each frame image, determining the difference between the pixel value of the image in the area and the area pixel value of the area in the background pixel distribution value; and regarding the area with a difference greater than a preset pixel difference as the head and tail section area.

[0072] In particular implementation, after determining the head-tail section area in each frame of the process image according to the pixel distribution value of each frame of the process image and the background pixel distribution value of the sliding channel, a connected domain analysis is performed on the head-tail section area in each frame of the process image to determine a plurality of sub-areas of the head-tail section area.

[0073] For each sub-area of each frame of the process image, a rectangularity of each sub-area is determined; the rectangularity is used to describe the ratio between the area of the sub-area and the area of the minimum circumscribed rectangle of the sub-area.

[0074] The sub-area with the rectangularity greater than or equal to a preset value is regarded as a first sub-area, and the sub-area with the rectangularity less than the preset value is regarded as a second sub-area; a plurality of segmentation lines are added to the minimum circumscribed rectangle of the second sub-area; and the maximum number of intersections between different segmentation lines and the second sub-area is regarded as the number of sub-areas containing head-tail sections in the second sub-area.

[0075] The sum of the number of first sub-areas and the number of second sub-areas is determined as the target number of head-tail sections of the target rod in the frame of the process image.

[0076] In the embodiment, the number of head-tail sections in each frame of the process image in the sliding process can be recognized by using a bidirectional dynamic segmentation method based on the image frame of the industrial camera.

[0077] In one embodiment, the segmentation lines include parallel segmentation lines parallel to the edges of the minimum circumscribed rectangle and diagonal segmentation lines parallel to the diagonal lines of the minimum circumscribed rectangle.

[0078] In particular implementation, after determining the sum of the number of first sub-areas and the number of second sub-areas as the target number of head-tail sections of the target rod in the frame of the process image, the maximum value of the target number of head-tail sections in each frame of the process image is determined; and when the maximum value is different from the set number of sheared sections of the rod shearing device, an alarm information is sent.

[0079] In the embodiment, whether the final number of head-tail sections CalSegCount is consistent with the set number of sheared sections of the high-speed shearing device is determined, and an alarm is sent in time when they are inconsistent.

[0080] As can be seen from the above example, the method for recognizing the number of head-tail sections of high-speed shearing based on image recognition can accurately determine the number of head-tail sections of high-speed shearing and send an alarm in real time.

[0081] In one embodiment, the method for recognizing the number of head-tail sections of high-speed shearing based on image recognition in the embodiment can be independently run in the form of an application program, or can be integrated into a production process control system as a subsystem and run after field debugging for actual production.

[0082] In the above embodiment, the image recognition based high-speed shearing head and tail section number recognition method of the embodiment of the application is a method for recognizing high-speed shearing head and tail section number with high accuracy and strong real-time performance. It predicts whether the head and tail section enters the rolling mill according to whether the number of the sliding head and tail section is consistent with the set number of the shearing section, and timely alarms, which can assist the operator to avoid the subsequent rolling piece from piling up and has good practical application value. Meanwhile, the application can replace the dedicated counting post worker to realize the reduction of staff and increase efficiency.

[0083] A specific embodiment is given below to illustrate the specific application of the method of the application. In the embodiment, an image recognition based high-speed shearing head and tail section number recognition method is proposed. The number of the head and tail section in each frame image is recognized by analyzing each frame image of the sliding process of the head or tail section from the side slide, and then the total number of the head or tail section in each cutting is calculated. If the calculated total number of the section is inconsistent with the set number of the high-speed shearing section, it may mean that the head or tail section enters the rolling mill, and timely alarm is performed to avoid the subsequent rolling piece from piling up. Meanwhile, the application can replace the dedicated counting post worker.

[0084] In the embodiment, first, an industrial camera is installed opposite the falling chute under the platform, and the camera field of view covers the entire side slide of the falling chute, as shown in Figure 2 The camera parameters and the installation distance are shown in Table 1.

[0085] Table 1 Camera and installation parameters

[0086]

[0087] When the high-speed shearing head or tail is cut, the high-speed shearing control system triggers the industrial camera to start shooting. The camera stops shooting after continuously shooting for Dt seconds at a frame rate of 300 fps. The value of Dt is settable, and the purpose is to ensure that the complete sliding process of each section can be shot. The application takes Dt = 20 seconds. For the continuous multiple frame images (Frame1-FrameN) of the entire sliding process, as shown in Figure 3 the image processing and recognition method proposed by the application is used to judge the number of the head and tail section in the image (Frame1SegCount-FrameNSegCount). Finally, the total number of the sliding section in this cutting head or tail is calculated by the function Max(FrameiSegCount). If the total number of the sliding section is inconsistent with the set number of the high-speed shearing section, timely alarm is performed.

[0088] The image processing and recognition method for judging the high-speed shearing head and tail section number is realized in two stages: the pre-processing stage and the post-processing stage, and the processing flow is shown in Figure 4 . In the pre-processing stage, the image frame is pre-processed to obtain the connected domain to be analyzed. In the post-processing stage, the bidirectional dynamic segmentation method is used to calculate the number of the head and tail section.

[0089] I. The pre-processing stage includes the following steps:

[0090] (1) Environmental background image preprocessing

[0091] A frame of environmental background image FrameBK is obtained from the camera, which is a three-channel color image, and needs to be converted into a single-channel grayscale image FrameBKS by channel conversion. Since the head and tail sections in the image are red steel, the head and tail sections have stronger contrast with the surrounding objects in the red channel image, so the three-channel color image is converted into a single-channel grayscale image FrameBKS by obtaining the red channel image.

[0092] In order to eliminate the influence of noise or noise points in the background image on image recognition, the application adopts convolution operation to filter the environmental background image. The parameters used in convolution operation are: the filter matrix Filter takes a 5x5 unit matrix (formula 1), the sliding step Stride takes 1, and the edge periphery is supplemented with 0. By doing the inner product of the filter matrix and the image matrix (each pixel point), the filtered image FrameBKSE (as shown in Figure 5 ) is obtained.

[0093]

[0094] (2) Head and tail section sliding process image preprocessing

[0095] When the high-speed shear cutter starts to cut, each frame of image of the head and tail section sliding process is obtained from the camera in real time until the end of the head and tail section sliding process. The application ensures that the images of the entire head and tail section sliding process can be obtained by giving a Dt value, such as Dt taking 20 seconds as mentioned above.

[0096] For each frame of head and tail section sliding image, the same preprocessing process as described in (1) is performed. The image frame of the head and tail section is Framei (i represents any frame from the first frame to the last frame), the single-channel grayscale image is FrameiS, and the filtered image is FrameiSE (as shown in Figure 6 ), and the specific processing process is not repeated here.

[0097] (3) Extracting head and tail section area

[0098] The application extracts the head and tail section from FrameiSE by using local threshold segmentation method. By subtracting the head and tail section image FrameiSE from the background image FrameBKSE, and selecting the image area whose pixel difference is greater than Offset (that is, the area where FrameiSE is "brighter" than FrameBKSE) from the operation result, as shown in formula (2).

[0099] g0(x)-g t(x) > Offset (2)

[0100] where g0(x) is the pixel distribution in FrameiSE, g t (x) is the pixel distribution in FrameBKSE, and Offset is a threshold. Offset is given externally, and in this embodiment, Offset = 100.

[0101] The head and tail region FrameiDy extracted from FrameiSE by local threshold segmentation is shown in Fig. 2. Figure 7

[0102] (4) Connected component analysis

[0103] Connected component analysis is performed on the head and tail region FrameiDy, and the entire region is divided into multiple sub-regions, i.e., CReg[0] and CReg[1], and further, sub-regions with areas between Smin and Smax are selected to filter out interference regions that are not head and tail, and the selected sub-regions can be one or multiple head and tails, as shown in the schematic diagram of connected component CReg containing only head and tail in Fig. 3. In this embodiment, Smin = 450 and Smax = 10000. Figure 8

[0104] II. Post-processing stage includes the following steps:

[0105] (1) Rectangularity judgment

[0106] For each sub-region CReg[i], the rectangularity CRegiRD of the sub-region is calculated using formula (3).

[0107]

[0108] where S0 is the area of the sub-region CReg[i], and S mer is the area of the minimum circumscribed rectangle of the sub-region CReg[i].

[0109] The following assumption is made when identifying the number of head and tail: when CReg[i] is rectangular, then the CReg[i] is a single head and tail, otherwise, the CReg[i] is a combination of multiple head and tails (in the sliding process of the head and tail, multiple segments can be intertwined or superimposed at a certain time).

[0110] Based on the above assumption, when CRegiRD > 0.85, CReg[i] is approximately rectangular, which indicates a single head and tail, otherwise, CReg[i] is a combination of multiple head and tails, and further identification is required.

[0111] (2) Calculate the parameters of the circumscribed rectangle of the sub-region

[0112] ​​If CReg[i] is a combination of multiple head-tail segments, the parameters of its circumscribed rectangle are calculated, including the coordinates of the four vertices, the diagonal BD, the line Line1 (start line) passing through point A and parallel to the diagonal BD, the line Line1 (end line) passing through point C and parallel to the diagonal BD, the line Line2 (start line) passing through point B and parallel to the X axis, the line Line2 (end line) passing through point D and parallel to the X axis, the distance MaxMoveLen1 between the two lines Line1, the distance MaxMoveLen2 between the two lines Line2, and the like, as shown in Figure 9

[0113] In this embodiment, the coordinates of the four vertices of the sub-region CReg[0] are A (206, 544), B (137, 374), C (264, 322), and D (333, 492), MaxMoveLen1 = 230, and MaxMoveLen2 = 160.

[0114] (3) Calculate the number of head-tail segments using the bidirectional dynamic segmentation method

[0115] The bidirectional dynamic segmentation method is to cut the sub-region CReg[i] from two directions (i.e., the diagonal direction and the parallel line direction) and calculate the number of intersection regions at each cutting. Cutting from two directions is to avoid the situation that the cutting line Line is parallel to a certain head-tail segment in the sub-region CReg[i], which leads to segmentation failure, so as to ensure the accuracy of the segment number identification.

[0116] In this embodiment, the following two ways of setting the cutting line are involved:

[0117] (1) Identify the number of head-tail segments based on the diagonal cutting auxiliary line

[0118] The line Line1 passing through point A and parallel to the diagonal BD is used as the diagonal cutting auxiliary line, which is translated from the starting position A according to the specified step length Step1, and the sub-region CReg[i] is cut until Line1 is translated to the end position C (the cumulative translation length is MaxMoveLen1). First, the number of intersection regions IS1Countj at each cutting is calculated, and then the maximum number of intersection regions MaxIS1 in the entire translation process is calculated. MaxIS1 is the number of head-tail segments CRegiSegCount identified in the sub-region CReg[i] (i.e., CRegiSegCount = MaxIS1). If the sub-region CReg[i] is close to a rectangle, as described in (1), then CRegiSegCount = 1. The number of head-tail segments CRegiSegCount identified in each sub-region is added (as shown in formula 4), and the number of head-tail segments FrameiSegCount identified by the diagonal segmentation method for the head-tail segment sliding image of the frame is obtained.​

[0119] FrameiSegCount =∑CRegiSegCount (4)

[0120] In the present application, for the sub-region CReg[0] in the frame, the translation step Step1 is taken as 10, the translation length MaxMoveLen1 is taken as 230, and the segmentation auxiliary line intersects with CReg[0] for 15 times in the whole cutting process (as shown in FIG. 4), and the number of intersection regions can be calculated after connected component analysis of each intersection (as shown in FIG. 5, there are 2 intersection regions), and the number of intersection regions of the 15 intersections is [2, 1, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], and the maximum intersection region number is 2, that is, the sub-region CReg[0] contains 2 head and tail segments. Figure 8 Figure 10 Figure 11 Figure 8 In the present application, for the sub-region CReg[1] in the frame, since it is a rectangle, that is, it only includes 1 head and tail segment. Therefore, the number of head and tail segments identified by the diagonal segmentation method for the head and tail segment sliding image of the frame is 3 segments.

[0121] (2) Identifying the number of head and tail segments based on parallel segmentation auxiliary lines

[0122] In the present application, for the sub-region CReg[0] in the frame, the translation step Step1 is taken as 10, the translation length MaxMoveLen1 is taken as 230, and the segmentation auxiliary line intersects with CReg[0] for 15 times in the whole cutting process (as shown in FIG. 4), and the number of intersection regions can be calculated after connected component analysis of each intersection (as shown in FIG. 5, there are 2 intersection regions), and the number of intersection regions of the 15 intersections is [2, 1, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], and the maximum intersection region number is 2, that is, the sub-region CReg[0] contains 2 head and tail segments.

[0123] In the present application, for the sub-region CReg[0] in the frame, the translation step Step1 is taken as 10, the translation length MaxMoveLen1 is taken as 230, and the segmentation auxiliary line intersects with CReg[0] for 15 times in the whole cutting process (as shown in FIG. 4), and the number of intersection regions can be calculated after connected component analysis of each intersection (as shown in FIG. 5, there are 2 intersection regions), and the number of intersection regions of the 15 intersections is [2, 1, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], and the maximum intersection region number is 2, that is, the sub-region CReg[0] contains 2 head and tail segments. Figure 8 Figure 12 Figure 13 ​​​​​As shown, there are 2 intersection regions, and the number of intersection regions of 15 intersections is [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 1], and the maximum intersection region number is 2, that is, the sub-region CReg[0] contains 2 head and tail segments. For the sub-region CReg[1] in the frame head and tail segment, since it is a rectangle, that is, it only includes 1 head and tail segment. Therefore, for the head and tail segment sliding image, the number of head and tail segments identified by the parallel segmentation method is 3 segments. Figure 10

[0124] (3) Comprehensive determination of the number of head and tail segments

[0125] The number of head and tail segments identified by the diagonal segmentation method and the parallel segmentation method is the maximum value (such as formula 5) of the calculation results of the two methods as the final head and tail segment number CalSegCount in the frame head and tail segment sliding image.

[0126] CalSegCount = Max(FrameiSegCount) (5)

[0127] (4) Identify the alarm

[0128] Determine whether the final head and tail segment number CalSegCount is consistent with the set cutting segment number of the high-speed shear, and if not, timely alarm.

[0129] As can be seen from the above example explanation process, the image recognition-based high-speed shear head and tail segment number identification method of the application can accurately determine the head and tail segment number of the high-speed shear, and real-time alarm.

[0130] The image recognition-based high-speed shear head and tail segment number identification method of the application can be independently run in the form of an application, or can be integrated into a production process control system as a subsystem and run after field debugging for actual production.

[0131] The image recognition-based high-speed shear head and tail segment number identification method of the embodiment is a high-accuracy and real-time high-speed shear head and tail segment number identification method. It predicts whether the head and tail segments enter the rolling mill according to whether the number of sliding head and tail segments is consistent with the set segment number, and real-time alarm can assist operators to avoid subsequent rolling stock stacking accidents, and has good practical application value. At the same time, the application can replace the dedicated counting post worker to achieve efficiency increase.

[0132] Of course, it can be understood that the above detailed process can also have other variations, and the related variations should fall within the protection scope of the application.

[0133] ​In the embodiment of the present application, process images of the sliding process of the head section and the tail section obtained by shearing the target bar by the bar shearing device are acquired; the head section and the tail section enter the waste hopper through the sliding channel; the head section and the tail section area in each frame of the process images are determined according to the pixel distribution value of each frame of the process images and the background pixel distribution value of the sliding channel; the pixel value of the head section and the tail section area is greater than the area pixel value of the corresponding head section and tail section area in the background pixel distribution value; for each frame of image, the head section and tail section area in the frame of image is subjected to connected domain analysis to determine a plurality of sub-areas of the head section and tail section area; for each sub-area of each frame of image, the rectangularity of each sub-area is determined; the rectangularity is used to describe the ratio between the area of the sub-area and the minimum circumscribed rectangle area of the sub-area; the sub-area with the rectangularity greater than or equal to a preset value is taken as a first sub-area; the sub-area with the rectangularity less than the preset value is taken as a second sub-area; a plurality of division lines are added to the minimum circumscribed rectangle of the second sub-area; the maximum number of intersections of different division lines and the second sub-area is taken as the number of head section and tail section contained in the second sub-area; the sum of the number of first sub-areas and the number of second sub-areas is determined as the target number of head section and tail section of the target bar in the frame of image; the maximum value in the target number of each frame of image is determined; when the maximum value is different from the set shearing section number of the bar shearing device, an alarm information is sent, compared with the technical solution of manually checking the shearing number of bar head and tail section in the prior art, the number of sliding head and tail section can be automatically determined and it is judged whether the number is consistent with the set shearing section number, so that it can be predicted whether the head and tail section enters the rolling mill bed, and real-time alarm can be made, which can assist the operator to avoid the steel stacking accident of subsequent rolling piece, and has good practical application value. At the same time, the present application can replace the full-time counting post worker, realize reduction of staff and increase of efficiency, improve the efficiency and accuracy of the monitoring of the bar shearing device, and reduce the monitoring cost of the bar shearing device.

[0134] In the embodiment of the present application, a monitoring device of a bar shearing device is also provided, as described in the following embodiment. Since the principle of solving the problem of the device is similar to the monitoring method of the bar shearing device, the implementation of the device can be referred to the implementation of the monitoring method of the bar shearing device, and the repeated parts will not be described again.

[0135] The embodiment of the present application also provides a monitoring device of a bar shearing device to improve the efficiency and accuracy of the monitoring of the bar shearing device and reduce the monitoring cost of the bar shearing device, as shown in Figure 15 The device comprises:

[0136] The process image acquisition module 1501 is configured to acquire process images of the sliding process of the head section and the tail section obtained by shearing the target bar by the bar shearing device; the head section and the tail section enter the waste hopper through the sliding channel;

[0137] The head-tail section area determination module 1502 is configured to determine a head-tail section area in each frame of the process image according to pixel distribution values of each frame of the process image and background pixel distribution values of the falling channel; a pixel value of the head-tail section area is greater than a region pixel value of a corresponding head-tail section area in the background pixel distribution values;

[0138] The sub-region determination module 1503 is configured to, for each frame of image, perform connected component analysis on the head-tail section area in the frame of image to determine a plurality of sub-regions of the head-tail section area;

[0139] The rectangularity determination module 1504 is configured to, for each sub-region of each frame of image, determine a rectangularity of each sub-region; the rectangularity is used to describe a ratio between an area of the sub-region and an area of a minimum circumscribed rectangle of the sub-region;

[0140] The sub-region head-tail section quantity determination module 1505 is configured to: take a sub-region with a rectangularity greater than or equal to a preset value as a first sub-region; take a sub-region with a rectangularity less than the preset value as a second sub-region; add a plurality of segmentation lines to the minimum circumscribed rectangle of the second sub-region; and take a maximum number of intersections of different segmentation lines and the second sub-region as a number of head-tail sections contained in the second sub-region;

[0141] The head-tail section quantity determination module 1506 is configured to determine a target number of head sections and tail sections of the target bar in the frame of image as a sum of a number of first sub-regions and the number of second sub-regions.

[0142] The alarm module 1507 is configured to issue an alarm information when the target number is different from a set number of sheared sections of the bar shearing device.

[0143] In an embodiment, the method further comprises:

[0144] The image acquisition module is configured to:

[0145] Acquire the process image of the target bar based on a camera arranged opposite to the falling chute under the steel rolling production platform.

[0146] In an embodiment, the method further comprises:

[0147] The pixel distribution value determination module is configured to:

[0148] Determine the pixel distribution value of each frame of image in the following manner:

[0149] Convert each frame of image from a three-channel color image to a single-channel grayscale image;

[0150] Perform filtering processing on the single-channel grayscale image of each frame of image by using convolution operation to obtain a filtered single-channel grayscale image;

[0151] determining a pixel distribution value of the filtered single-channel grayscale image.

[0152] In one embodiment, the head-tail region determining module is specifically configured to:

[0153] For each region in each frame of image, determining a difference value between pixel values of the image in the region and region pixel values of the region in the background pixel distribution value.

[0154] regarding the region as the head-tail region if the difference value is greater than a preset pixel difference.

[0155] In one embodiment, the split line includes a parallel split line parallel to a side of the minimum bounding rectangle and a diagonal split line parallel to a diagonal line of the minimum bounding rectangle.

[0156] Embodiments of the application provide a computer device for implementing all or part of the above-mentioned monitoring method of the bar shearing device.

[0157] A processor, a memory, a communications interface and a bus; wherein the processor, the memory and the communications interface complete mutual communication through the bus; the communications interface is used for realizing information transmission between related devices; the computer device can be a desktop computer, a tablet computer and a mobile terminal, and the like, and the embodiments are not limited thereto. In the embodiments, the computer device can be implemented by referring to the embodiments of the monitoring method of the bar shearing device and the embodiments of the monitoring device of the bar shearing device, and the contents are incorporated herein, and the repeated parts will not be described herein.

[0158] Figure 16 A schematic block diagram of a system structure of the computer device 1000 of the embodiments of the application is shown in FIG. 1. As shown in the figure, the computer device 1000 can include a central processor 1001 and a memory 1002; the memory 1002 is coupled to the central processor 1001. It is worth noting that the structure shown in the figure is exemplary; other types of structures can also be used to supplement or replace the structure to realize telecommunication functions or other functions. Figure 16 Figure 16 The structure shown in the figure is exemplary; other types of structures can also be used to supplement or replace the structure to realize telecommunication functions or other functions.

[0159] In one embodiment, the monitoring function of the bar shearing device can be integrated into the central processor 1001. The central processor 1001 can be configured to perform the following control:

[0160] ​The process image of the head and tail sections of the target bar being cut by the bar shearing device and then sliding down is obtained; the head and tail sections enter the waste hopper through the sliding channel;

[0161] Based on the pixel distribution values ​​of each frame in the process image and the background pixel distribution values ​​of the slip channel, the head and tail regions in each frame are determined; the pixel values ​​of the head and tail regions are greater than the corresponding region pixel values ​​in the background pixel distribution values.

[0162] For each frame of image, perform connected component analysis on the head and tail regions of that frame to determine multiple sub-regions of the head and tail regions;

[0163] For each sub-region of each frame image, determine the rectangularity of each sub-region; the rectangularity is used to describe the ratio between the area of ​​the sub-region and the area of ​​the minimum bounding rectangle of the sub-region.

[0164] The sub-regions with a rectangularity greater than or equal to a preset value are designated as the first sub-region; the sub-regions with a rectangularity less than the preset value are designated as the second sub-region; multiple dividing lines are added to the minimum bounding rectangle of the second sub-region; the maximum number of intersections between different dividing lines and the second sub-region is taken as the number of lines containing head and tail segments in the second sub-region.

[0165] The sum of the number of the first sub-region and the number of the bars in the second sub-region is determined as the target number of the head and tail segments of the target bar in the frame image.

[0166] Determine the maximum value among the target quantities in each frame of the image; when the maximum value is different from the set number of cutting segments of the bar shearing device, issue an alarm message.

[0167] In another embodiment, the monitoring device of the bar shearing device can be configured separately from the central processing unit 1001. For example, the monitoring device of the bar shearing device can be configured as a chip connected to the central processing unit 1001, and the monitoring function of the bar shearing device can be realized through the control of the central processing unit.

[0168] like Figure 16 As shown, the computer device 1000 may further include: a communication module 1003, an input unit 1004, an audio processor 1005, a display 1006, and a power supply 1007. It is worth noting that the computer device 1000 does not necessarily need to include... Figure 16 All components shown; in addition, the computer device 1000 may also include Figure 16 For components not shown, please refer to existing technologies.

[0169] like Figure 16As shown, the central processing unit 1001, which is sometimes also referred to as a controller or operation control, can include a microprocessor or other processor device and / or logic device, which receives input and controls the operation of the various components of the computer device 1000.

[0170] The memory 1002, for example, can be one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. Information relating to failures can be stored, and in addition, programs for executing the information can be stored. The central processing unit 1001 can execute the programs stored in the memory 1002 to achieve information storage or processing, etc.

[0171] The input unit 1004 provides input to the central processing unit 1001. The input unit 1004 is, for example, a key or touch input device. The power supply 1007 is used to provide power to the computer device 1000. The display 1006 is used to display display objects such as images and text. The display can be, for example, an LCD display, but is not limited thereto.

[0172] The memory 1002 can be a solid state memory such as a read only memory (ROM), a random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROM, etc. The memory 1002 can also be some other type of device. The memory 1002 includes a buffer memory 1021 (sometimes referred to as a buffer). The memory 1002 can include an application / function storage section 1022 for storing application programs and function programs or for storing a flow for executing the operation of the computer device 1000 by the central processing unit 1001.

[0173] The memory 1002 can also include a data storage section 1023 for storing data such as contacts, digital data, pictures, sounds, and / or any other data used by the computer device. A driver storage section 1024 of the memory 1002 can include various drivers of the computer device for communication functions and / or for executing other functions of the computer device such as a messaging application, an address book application, etc.

[0174] The communication module 1003 is a transmitter / receiver 1003 that transmits and receives signals via an antenna 1008. The communication module (transmitter / receiver) 1003 is coupled to the central processing unit 1001 to provide input signals and receive output signals, which can be the same as in the case of a conventional mobile communication terminal.

[0175] Based on different communication technologies, multiple communication modules 1003, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module, etc., can be provided in the same computer device. The communication module (transmitter / receiver) 1003 is also coupled to a speaker 1009 and a microphone 1010 via an audio processor 1005 to provide audio output via the speaker 1009 and to receive audio input from the microphone 1010 to enable typical telecommunication functions. The audio processor 1005 can include any suitable buffers, decoders, amplifiers, etc. In addition, the audio processor 1005 is coupled to the central processor 1001 to enable recording of audio on the local machine via the microphone 1010 and to enable playing of stored audio on the local machine via the speaker 1009.

[0176] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the monitoring method of the bar shearing device.

[0177] The embodiment of the present application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to realize the monitoring method of the bar shearing device.

[0178] In the embodiment of the present application, the process images of the sliding process of the head section and the tail section of the target bar obtained by the bar shearing device are acquired; the head section and the tail section enter the waste hopper through the sliding channel; the head section and the tail section area in each frame of image is determined according to the pixel distribution value of each frame of image in the process image and the background pixel distribution value of the sliding channel; the pixel value of the head section and the tail section area is greater than the area pixel value of the corresponding head section and tail section area in the background pixel distribution value; for each frame of image, the connected domain analysis is performed on the head section and tail section area in the frame of image to determine a plurality of sub-areas of the head section and tail section area; for each sub-area of each frame of image, the rectangularity of each sub-area is determined; the rectangularity is used to describe the ratio between the area of the sub-area and the minimum circumscribed rectangle area of the sub-area; the sub-area with the rectangularity greater than or equal to a preset value is taken as a first sub-area; the sub-area with the rectangularity less than the preset value is taken as a second sub-area; a plurality of division lines are added to the minimum circumscribed rectangle of the second sub-area; the maximum number of intersections of different division lines and the second sub-area is taken as the number of head and tail sections contained in the second sub-area; the sum of the number of first sub-areas and the number of second sub-areas is determined as the target number of the head section and the tail section of the target bar in the frame of image; the maximum value in the target number of each frame of image is determined; when the maximum value is different from the set shearing section number of the bar shearing device, an alarm information is sent; compared with the technical solution of checking the shearing number of the head and tail sections of the bar by manual operation in the prior art, the number of the sliding head and tail sections can be automatically determined and it is judged whether the number is consistent with the set shearing section number, so that it can be predicted whether the head and tail sections enter the rolling mill and real-time alarm can be sent to assist the operator to avoid the steel stacking accident of the subsequent rolling piece, and the present application has good practical application value. Meanwhile, the present application can replace the full-time counting post worker, realize the reduction of staff and increase of efficiency, improve the monitoring efficiency and accuracy of the bar shearing device, and reduce the monitoring cost of the bar shearing device.

[0179] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer-readable program code.

[0180] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0181] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0182] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0183] The above-described specific embodiments, the purpose, technical solutions and advantages of the present application are further described in detail, it should be understood that the above-described only for the specific embodiments of the present application has, and is not used to limit the scope of protection of the present application, any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application, should be included within the scope of protection of the present application.

Claims

1. A monitoring method for a bar shearing device, characterized in that, include: Acquire process images of the sliding process of the head and tail sections of the target bar obtained by the bar shearing device; The head section and tail section enter the waste hopper through a sliding channel; Based on the pixel distribution values ​​of each frame in the process image and the background pixel distribution values ​​of the slip channel, the head and tail regions in each frame are determined; the pixel values ​​of the head and tail regions are greater than the corresponding region pixel values ​​in the background pixel distribution values. For each frame of image, perform connected component analysis on the head and tail regions of that frame to determine multiple sub-regions of the head and tail regions; For each sub-region of each frame image, determine the rectangularity of each sub-region; the rectangularity is used to describe the ratio between the area of ​​the sub-region and the area of ​​the minimum bounding rectangle of the sub-region; The sub-regions with a rectangularity greater than or equal to a preset value are designated as the first sub-region; the sub-regions with a rectangularity less than the preset value are designated as the second sub-region; multiple dividing lines are added to the minimum bounding rectangle of the second sub-region. The maximum number of intersections between different dividing lines and the second sub-region is taken as the number of lines containing head and tail segments in the second sub-region; the dividing lines include: parallel dividing lines parallel to the sides of the minimum bounding rectangle, and diagonal dividing lines parallel to the diagonal line connecting the diagonals of the minimum bounding rectangle; The sum of the number of the first sub-regions and the number of bars containing head and tail segments in the second sub-regions is determined as the target number of head and tail segments of the target bar in this frame image. Determine the maximum value among the target quantities in each frame of the image; when the maximum value is different from the set number of cutting segments of the bar shearing device, issue an alarm message.

2. The method as described in claim 1, characterized in that, Also includes: The process images of the target bar are acquired using a camera positioned opposite the material drop chute below the steel rolling production platform.

3. The method as described in claim 1, characterized in that, Also includes: The pixel distribution values ​​for each frame of the image are determined as follows: Convert each frame of the image from a three-channel color image to a single-channel grayscale image; Convolution operation is used to filter the single-channel grayscale image of each frame to obtain the filtered single-channel grayscale image. Determine the pixel distribution values ​​of the single-channel grayscale image after filtering.

4. The method as described in claim 1, characterized in that, Based on the pixel distribution values ​​of each frame in the process image and the background pixel distribution values ​​of the slip channel, the head and tail regions in each frame are determined, including: For each region in each frame of the image, determine the difference between the pixel value of the image in that region and the region pixel value in the background pixel distribution value; Regions with a difference greater than the preset pixel difference are designated as the beginning and end segments.

5. A monitoring device for a bar shearing apparatus, characterized in that, include: The process image acquisition module is used to acquire process images of the sliding process of the head and tail sections of the target bar obtained by the bar shearing device; The head section and tail section enter the waste hopper through a sliding channel; The head and tail region determination module is used to determine the head and tail regions in each frame of the process image based on the pixel distribution values ​​of each frame and the background pixel distribution values ​​of the sliding channel; the pixel values ​​of the head and tail regions are greater than the corresponding region pixel values ​​in the background pixel distribution values. The sub-region determination module is used to perform connected component analysis on the head and tail regions of each frame of image to determine multiple sub-regions of the head and tail regions. The rectangularity determination module is used to determine the rectangularity of each sub-region for each frame of image; the rectangularity is used to describe the ratio between the area of ​​the sub-region and the area of ​​the minimum bounding rectangle of the sub-region; The sub-region includes a module for determining the number of head and tail segments, which is used to designate sub-regions with a rectangularity greater than or equal to a preset value as first sub-regions; designate sub-regions with a rectangularity less than the preset value as second sub-regions; and add multiple dividing lines to the minimum bounding rectangle of the second sub-region. The maximum number of intersections between different dividing lines and the second sub-region is taken as the number of lines containing head and tail segments in the second sub-region; the dividing lines include: parallel dividing lines parallel to the sides of the minimum bounding rectangle, and diagonal dividing lines parallel to the diagonal line connecting the diagonals of the minimum bounding rectangle; The head and tail segment quantity determination module is used to determine the target quantity of the head and tail segments of the target bar in the frame image by summing the number of the first sub-region and the number of bars containing head and tail segments in the second sub-region. An alarm module is used to determine the maximum value of the target quantity in each frame of the image; when the maximum value is different from the set number of cutting segments of the bar shearing device, an alarm message is issued.

6. The apparatus as claimed in claim 5, characterized in that, Also includes: Image acquisition module, used for: The process images of the target bar are acquired using a camera positioned opposite the material drop chute below the steel rolling production platform.

7. The apparatus as claimed in claim 5, characterized in that, Also includes: The pixel distribution value determination module is used for: The pixel distribution values ​​for each frame of the image are determined as follows: Convert each frame of the image from a three-channel color image to a single-channel grayscale image; Convolution operation is used to filter the single-channel grayscale image of each frame to obtain the filtered single-channel grayscale image. Determine the pixel distribution values ​​of the single-channel grayscale image after filtering.

8. The apparatus as claimed in claim 5, characterized in that, The module for determining the beginning and end segments is specifically used for: For each region in each frame of the image, determine the difference between the pixel value of the image in that region and the region pixel value in the background pixel distribution value; Regions with a difference greater than the preset pixel difference are designated as the beginning and end segments.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 4.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 4.

Images