Raw material blank inclination detection method, device, equipment and readable storage medium

Abstract

The present application is a kind of raw material blank inclination detection method, device, equipment and readable storage medium, the raw material blank inclination detection method, it includes the following steps: collecting the image of raw material blank, to obtain the position of the two end portions of raw material blank in the process of lifting;Detect the pixel position of raw material blank in the image;According to the position of the two end portions of raw material blank in pixel position is calibrated, to obtain the mapping relationship between the position of the two end portions of raw material blank in the image and its in actual scene;According to the mapping relationship, the inclination of raw material blank is detected.The present application solves the technical problem that raw material blank cannot be effectively detected in the process of lifting.

Description

Technical Field

[0001] This invention relates to the field of bar and wire production technology, and in particular to a method, apparatus, equipment, and readable storage medium for detecting the tilt of raw material billets. Background Technology

[0002] Currently, in the production of bars and wire rods, the freshly cast billets (typically square billets with a side length of approximately 20cm and a length of approximately 10 meters) need to be transported from bottom to top onto the furnace feed roller conveyor via a chain elevator for subsequent production operations. During the billet lifting process, due to equipment malfunctions, the two ends of the billet may be at different heights, leading to tilting and material spillage accidents, which can damage the equipment.

[0003] Currently, most bar and wire rod production lines rely on operators to visually inspect the billets via video monitoring to determine if they tilt during the lifting process. This method has the following drawbacks:

[0004] First, the workload of operators is extremely high, which not only consumes manpower but also results in significant errors.

[0005] Second, manual visual inspection has low precision and accuracy.

[0006] Third, it cannot achieve automated closed-loop control, resulting in low production efficiency;

[0007] Fourth, it is inconsistent with the current goal of reducing personnel and increasing efficiency.

[0008] There is currently no effective solution to the problem that the tilting of the raw billet cannot be effectively detected during the lifting process in related technologies.

[0009] Therefore, based on years of experience and practice in related industries, the inventor proposes a method, apparatus, equipment, and readable storage medium for detecting the tilt of raw billets, in order to overcome the shortcomings of the prior art. Summary of the Invention

[0010] The purpose of this invention is to provide a method, apparatus, equipment, and readable storage medium for detecting the tilt of raw billets. By employing image processing technology, it can automatically and accurately detect whether the raw billet is tilted during the billet lifting process. When the tilt of the raw billet is detected, the detection result can be fed back in a timely manner, thereby improving the accuracy and efficiency of detection and providing a technical means for realizing unmanned automated production.

[0011] The objective of this invention can be achieved using the following technical solutions:

[0012] This invention provides a method for detecting the tilt of a raw material billet, comprising the following steps:

[0013] Acquire images of the raw material billet to determine the positions of both ends of the raw material billet during the lifting process;

[0014] Detect the pixel position of the raw material blank in the image;

[0015] The positions of the two ends of the raw material blank are calibrated based on the pixel positions to obtain the mapping relationship between the positions of the two ends of the raw material blank in the image and their actual scene;

[0016] The tilting condition of the raw material billet is detected based on the mapping relationship.

[0017] In a preferred embodiment of the present invention, detecting the pixel position of the raw material blank in the image includes:

[0018] Extract the grayscale value of the red channel from the image to obtain a first grayscale image;

[0019] Perform contrast enhancement processing on the first grayscale image to obtain a first grayscale enhanced image;

[0020] The first grayscale enhanced image is binarized to obtain a binarized image;

[0021] Select an image region containing the raw material billet from the binarized image;

[0022] Extract the image heights of both ends of the raw material blank within the image area.

[0023] In a preferred embodiment of the present invention, selecting an image region containing the raw material billet in the binarized image includes:

[0024] Traverse all image regions in the binarized image and calculate the area of ​​each image region;

[0025] The area of ​​each of the image regions is compared with a preset judgment value;

[0026] If the area of ​​the image region is greater than the preset determination value, then the image region is the image region where the raw material billet is located;

[0027] If the area of ​​each of the image regions is smaller than the preset determination value, then the raw material blank does not exist within the image region.

[0028] In a preferred embodiment of the present invention, extracting the image heights of both ends of the raw material blank in the image region includes:

[0029] In a two-dimensional coordinate system, obtain the coordinates of all points of the raw material billet in the image area;

[0030] Traverse all coordinate values ​​of the raw material blank in the length direction and obtain a set of all coordinate values ​​of the raw material blank in the height direction to determine the image height of both ends of the raw material blank.

[0031] In a preferred embodiment of the present invention, the step of traversing all coordinate values ​​of the raw material billet in the length direction and obtaining a set of all coordinate values ​​of the raw material billet in the height direction to determine the image height of both ends of the raw material billet includes: in the two-dimensional coordinate system,

[0032] Traverse all coordinate values ​​of the raw material billet in the length direction from smallest to largest, and obtain the first set of all coordinate values ​​of the raw material billet in the height direction;

[0033] The median value of all coordinate values ​​in the first set is taken as the image height of the first end of the raw material billet;

[0034] Traverse all coordinate values ​​of the raw material billet in the length direction from largest to smallest, and obtain a second set of all coordinate values ​​of the raw material billet in the height direction;

[0035] The median value of all coordinate values ​​in the second set is obtained as the image height of the second end of the raw material billet.

[0036] In a preferred embodiment of the present invention, the step of calibrating the positions of the two ends of the raw material blank according to the pixel positions to obtain the mapping relationship between the positions of the two ends of the raw material blank in the image and their actual scene includes: during the lifting process of the raw material blank...

[0037] After each preset time interval, the upward movement of the raw material billet is stopped, and an image of each raw material billet in its stopped state is acquired.

[0038] Obtain the upward movement distance of the raw material billet within each preset time period;

[0039] Establish a correspondence between the image of the raw material billet in the stopped state and the upward movement of the raw material billet within the preset time period;

[0040] Obtain the mapping relationship between the image height of both ends of the raw material billet in each image and the upward movement of the raw material billet within the corresponding preset time period.

[0041] In a preferred embodiment of the present invention, detecting the tilting state of the raw material billet according to the mapping relationship includes: during the lifting process of the raw material billet,

[0042] The image of the raw material billet is acquired in real time, and the actual image height of both ends of the raw material billet is obtained.

[0043] Find the interval corresponding to the actual image height of the two ends of the raw material blank in the mapping relationship between the image height of the two ends of the raw material blank and the upward movement of the raw material blank within the preset time;

[0044] Calculate the actual lifting height of both ends of the raw material billet from its initial state.

[0045] Calculate the actual height difference between the two ends of the raw material billet;

[0046] If the actual height difference is greater than the preset height difference threshold, the raw material billet tilts.

[0047] If the actual height difference is less than or equal to the preset height difference threshold, then the raw material billet has not tilted.

[0048] In a preferred embodiment of the present invention, the formula for calculating the actual lifting height of the two ends of the raw material billet from the initial state is as follows:

[0049]

[0050] Among them, L left L represents the actual lifting height of the first end of the raw material billet. right h is the actual lifting height of the second end of the raw material billet. left h is the image height of the first end of the raw billet in a two-dimensional coordinate system. right is the image height of the second end of the raw material billet; n is the number of times the image is acquired.

[0051] In a preferred embodiment of the present invention, during the process of acquiring images of the raw material billet, an industrial camera is used to capture the lifting process of the raw material billet by the hoist, and both ends of the raw material billet are always visible in the image.

[0052] In a preferred embodiment of the present invention, the industrial camera transmits the captured image to a server, and the server determines whether the raw material billet is tilted; if the raw material billet is tilted, the server generates an alarm signal.

[0053] This invention provides a raw material billet tilt detection device, comprising:

[0054] An image acquisition unit is used to acquire images of the raw material billet to obtain the positions of the two ends of the raw material billet during the lifting process;

[0055] A raw material billet detection unit is used to detect the pixel position of the raw material billet in the image;

[0056] The mapping relationship acquisition unit is used to calibrate the positions of the two ends of the raw material blank according to the pixel position, so as to obtain the mapping relationship between the positions of the two ends of the raw material blank in the image and their actual scene;

[0057] The tilt detection unit is used to detect the tilt status of the raw material billet according to the mapping relationship.

[0058] In a preferred embodiment of the present invention, the image acquisition unit is an industrial camera, which is positioned facing the elevator to ensure that the two ends of the raw material billet are always displayed in the acquired image.

[0059] The present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for detecting the tilt of raw billets.

[0060] The present invention provides a computer-readable storage medium storing a computer program for performing the above-described method for detecting the tilt of raw billets.

[0061] As described above, the features and advantages of the raw material billet tilt detection method, apparatus, equipment, and readable storage medium of the present invention are as follows: During the raw material billet lifting process, images of the raw material billet are acquired to obtain the positions of the two ends of the raw material billet during the lifting process. The pixel positions of the raw material billet in the image are detected, and the positions of the two ends of the raw material billet are calibrated according to the pixel positions, thereby obtaining the mapping relationship between the positions of the two ends of the raw material billet in the image and their actual scene. The tilt status of the raw material billet is detected according to this mapping relationship, and the detection result is uploaded for timely processing by the staff. The above method can form a closed-loop control for raw material billet tilt detection, which can not only effectively improve the accuracy of detection and production efficiency, but also greatly reduce the labor intensity of operators, providing a technical means for realizing automated lifting of raw material billets. Attached Figure Description

[0062] The accompanying drawings are intended only to illustrate and explain the present invention and do not limit the scope of the invention.

[0063] in:

[0064] Figure 1 This is one of the flowcharts for the raw material billet tilt detection method of the present invention.

[0065] Figure 2 This is the second flowchart of the raw material billet tilt detection method of the present invention.

[0066] Figure 3 This is the third flowchart of the raw material billet tilt detection method of the present invention.

[0067] Figure 4 This is the fourth flowchart of the raw material billet tilt detection method of the present invention.

[0068] Figure 5 This is the fifth flowchart of the raw material billet tilt detection method of the present invention.

[0069] Figure 6 This is the sixth flowchart of the raw material billet tilt detection method of the present invention.

[0070] Figure 7 This is the seventh flowchart of the raw material billet tilt detection method of the present invention.

[0071] Figure 8 : This is a schematic diagram showing the location of the industrial camera in the raw material billet tilt detection method of the present invention.

[0072] Figure 9 This is a schematic diagram of the position of the raw material billet in a two-dimensional coordinate system in the raw material billet tilt detection method of the present invention.

[0073] Figure 10 : This is a control principle diagram of the raw material billet tilt detection method of the present invention.

[0074] Figure 11 : This is a structural block diagram of the raw material billet tilt detection device of the present invention.

[0075] The reference numerals in the accompanying drawings of this invention are:

[0076] 1. Raw material blank; 2. Industrial camera;

[0077] 3. Hoist; 4. Switch;

[0078] 5. Server; 6. Controller;

[0079] 100. Image acquisition unit; 200. Raw material billet detection unit;

[0080] 300. Mapping relationship acquisition unit; 400. Tilt detection unit. Detailed Implementation

[0081] To provide a clearer understanding of the technical features, objectives, and effects of the present invention, specific embodiments of the present invention will now be described with reference to the accompanying drawings.

[0082] Implementation Method 1

[0083] like Figure 1 As shown, the present invention provides a method for detecting the tilt of a raw billet, which includes the following steps:

[0084] Step S1: Acquire an image of the raw material billet 1 to obtain the positions of both ends of the raw material billet 1 during the lifting process;

[0085] Specifically, such as Figure 8 As shown, during the process of acquiring images of the raw material billet 1, an industrial camera 2 is set in the direction directly facing the elevator 3. The industrial camera 2 acquires the lifting process of the raw material billet 1 by the elevator 3, and it is necessary to ensure that during the lifting process of the raw material billet 1, both ends 9 (i.e., the first end and the second end) of the raw material billet 1 can always be displayed in the acquired images.

[0086] Furthermore, in the actual production process, the raw material billet 1 can be lifted by the elevator 3. The elevator 3 can be, but is not limited to, a chain elevator.

[0087] Step S2: Detect the pixel position of raw material billet 1 in the image;

[0088] In an optional embodiment of the present invention, such as Figure 2 As shown, step S2 includes:

[0089] Step S201: Extract the grayscale value of the red channel in the image to obtain the first grayscale image Img_red;

[0090] In this case, the raw material billet 1 is at a high temperature, making its body red. A color image (i.e., the acquired image) includes three color channels: R (red channel), G (green channel), and B (blue channel). The gray value of the billet area in the red channel is higher in the image. Therefore, only the gray value of the red channel in the image is selected, and the corresponding area of ​​the red channel is used to generate the first grayscale image Img_red.

[0091] Step S202: Perform contrast enhancement processing on the first grayscale image Img_red to obtain the first grayscale enhanced image Img_enhangced;

[0092] Specifically, in the process of contrast enhancement processing of the first grayscale image Img_red, the calculation formula that can be used is G. new =G old ×a+N, where G old G represents the original grayscale value of the image. new The image enhancement grayscale value is represented by a and N, which are parameters (adjustable as needed). Generally, a = 3 and N = -400 can be set. If G... new <0, then G new =0; if G new >255, then G new =255. After processing, the first grayscale enhanced image Img_enhangced is obtained.

[0093] Step S203: Binarize the first grayscale enhanced image Img_enhangced to obtain a binary image Img_twovalue;

[0094] Specifically, the first grayscale enhanced image Img_enhangced is binarized using a threshold segmentation algorithm. If G≦125 (this value can be adjusted according to the actual situation), then G=0; if G>125, then G=255; where G is the grayscale value of the image. After processing, the binarized image Img_twovalue is obtained. The binarized image Img_twovalue may contain multiple image regions, but only one image region corresponds to the raw billet body, and the other image regions are background noise.

[0095] Step S204: Select the image region containing the raw material billet 1 in the binarized image Img_twovalue;

[0096] Furthermore, such as Figure 3 As shown, step S204 includes:

[0097] Step S2041: Traverse all image regions in the binarized image Img_twovalue and calculate the area S of each image region. O ;

[0098] Step S2042: Calculate the area S of each image region. O Each value is compared with a preset judgment value σ (σ can generally be adjusted according to the actual situation; in this invention, the value can be 500).

[0099] Step S2043: If the area S of the image region O Greater than the preset judgment value σ (i.e., S) O If >σ), then the image region is the image region where raw material billet 1 is located (the connected region of raw material billet in the image is the largest);

[0100] Step S2044: If the area S of all image regions O All are less than the preset judgment value σ (i.e., S) O If <σ), then it is assumed that there is no raw material billet 1 in the image area.

[0101] Step S205: Extract the image heights of both ends of the raw material billet 1 from the image area.

[0102] Furthermore, such as Figure 4 , Figure 9 As shown, step S205 includes:

[0103] Step S2051: In a two-dimensional coordinate system, obtain the coordinates of all points of the raw material billet in the image area;

[0104] Step S2052: Traverse all coordinate values ​​of raw material billet 1 in the length direction and obtain the set of all coordinate values ​​of raw material billet 1 in the height direction to determine the image height of both ends of raw material billet 1.

[0105] Furthermore, such as Figure 5 , Figure 9 As shown, step S2052 includes:

[0106] Step S20521: In a two-dimensional coordinate system, traverse the raw material billet 1 from smallest to largest along the length direction (i.e., from the minimum value X on the X-axis). min Start by iterating up to X. min +h) all coordinate values, and obtain the first set {Y} of all coordinate values ​​of raw material billet 1 in the height direction (i.e., the Y coordinate axis). left};

[0107] Step S20522: Obtain the first set {Y} left The median value of all coordinate values ​​in the image is used as the image height h of the first end of raw billet 1 (i.e., the left end of raw billet 1). left ;

[0108] Step S20523: In a two-dimensional coordinate system, traverse the raw material billet 1 from largest to smallest along the length direction (i.e., from the maximum X coordinate X). max Start by iterating up to X. max -h) all coordinate values, and obtain the second set {Y} of all coordinate values ​​of raw material billet 1 in the height direction (i.e., the Y coordinate axis). right};

[0109] Step S20524: Obtain the second set {Y} right The median value of all coordinates in the image is used as the image height h of the second end of raw billet 1 (i.e., the right end of raw billet 1). right .

[0110] Where h can be selected according to the actual situation on site, and in this invention, h = 30 can be taken.

[0111] Step S3: Due to distortion and other factors in the lens of the industrial camera 2, and the tilt angle of the industrial camera 2 during installation, it is necessary to calibrate in advance when positioning the two ends of the raw material billet 1 to obtain the mapping relationship between the position of the two ends of the raw material billet 1 in the image and its actual scene.

[0112] In an optional embodiment of the present invention, such as Figure 6 As shown, step S3 includes:

[0113] Step S301: During the lifting process of raw material billet 1, after each preset time of lifting raw material billet 1, stop the upward movement of raw material billet 1 and acquire an image of each raw material billet in the stopped state;

[0114] Step S302: Obtain the upward movement distance of raw material billet 1 within each preset time period;

[0115] Step S303: Establish the correspondence between the image of raw billet 1 in the stopped state and the upward movement of raw billet 1 within the corresponding preset time;

[0116] Step S304: Obtain the mapping relationship between the image height of both ends of the raw material billet 1 in each image and the upward movement of the raw material billet 1 within the corresponding preset time.

[0117] Specifically, coordinate mapping is performed under normal operating conditions of the elevator 3 (assuming that the lifting heights of the two ends of the raw material billet 1 are equal at this time). The elevator 3 lifts a raw material billet 1 from the bottom to the top, stopping after every 1 second (this preset time can be adjusted; the shorter the time, the higher the calibration accuracy). At this time, an image data is acquired, and the lifting distance is obtained (this distance is calculated by the encoder installed on the equipment), establishing image data P. n and increase distance L n The correspondence between them.

[0118] For each image, the aforementioned end detection algorithm is called to obtain the positions of the two ends of the raw material billet 1 in the image. And the actual lifting distance L n A set of mapping relationships between them is shown in Table 1 below:

[0119]

[0120] Table 1

[0121] Step S4: Detect the tilting condition of raw material billet 1 according to the mapping relationship.

[0122] In an optional embodiment of the present invention, such as Figure 7 As shown, step S4 includes:

[0123] Step S401: During the lifting process of the raw material billet 1, the image of the raw material billet 1 is acquired in real time, and the actual image height h of the two ends of the raw material billet 1 is obtained according to the above step S2. left and h right ;

[0124] Step S402: Find the interval corresponding to the actual image height of the two ends of the raw material billet 1 in the mapping relationship between the image height of the two ends of the raw material billet and the upward movement of the raw material billet within the corresponding preset time (which can be found in Table 1 above);

[0125] Step S403: Calculate the actual lifting height L at both ends of the raw material billet 1 from its initial state. left and L right The formula for calculating the actual lifting height of the two ends of the raw material billet 1 from its initial state is as follows:

[0126]

[0127] Among them, L left L represents the actual lifting height of the first end of the raw material billet. right h is the actual lifting height of the second end of the raw material billet. left h is the image height of the first end of the raw billet in a two-dimensional coordinate system. right is the image height of the second end of the raw material billet; n is the number of times the image is acquired.

[0128] Step S404: Calculate the actual height difference between the two ends of the raw material billet 1 (i.e., δ = L). left -L right );

[0129] Step S405: If the actual height difference is greater than the preset height difference threshold d (i.e., δ > d), then the raw material billet 1 tilts; if the actual height difference is less than or equal to the preset height difference threshold d (i.e., δ ≤ d), then the raw material billet 1 does not tilt. The height difference threshold can be selected according to the actual situation on site; in this embodiment, the height difference threshold d can be selected as 30cm.

[0130] In an optional embodiment of the present invention, such as Figure 10 As shown, industrial camera 2 is connected to server 5 and controller 6 via switch 4. Industrial camera 2 transmits the acquired images to server 5. Server 5 uses the method described above to determine whether the raw material billet 1 is tilted. If the raw material billet 1 is tilted, server 5 generates an alarm signal and transmits the alarm signal to controller 6, which then performs subsequent processing. Controller 6 can be, but is not limited to, a PLC controller.

[0131] The features and advantages of the raw billet tilt detection method of the present invention are as follows:

[0132] This billet tilt detection method, during the lifting process of billet 1, acquires images of billet 1 to obtain the positions of both ends of billet 1 during the lifting process, detects the pixel positions of billet 1 in the image, and calibrates the positions of both ends of billet 1 based on the pixel positions, thereby obtaining the mapping relationship between the positions of both ends of billet 1 in the image and their actual scene. The tilt status of billet 1 is detected based on this mapping relationship, and the detection results are uploaded for timely processing by operators. The billet tilt detection method of this invention can form a closed-loop control for the tilt detection of billet 1, which can not only effectively improve the detection accuracy and production efficiency, but also greatly reduce the labor intensity of operators, providing a technical means for realizing automated lifting of billets.

[0133] Implementation Method 2

[0134] like Figure 11 As shown, the present invention provides a raw material billet tilt detection device, which includes:

[0135] The image acquisition unit 100 is used to acquire images of the raw material billet 1 to obtain the positions of the two ends of the raw material billet 1 during the lifting process;

[0136] The raw material billet detection unit 200 is used to detect the pixel position of the raw material billet 1 in the image;

[0137] The mapping relationship acquisition unit 300 is used to calibrate the positions of the two ends of the raw material billet 1 according to the pixel position, so as to obtain the mapping relationship between the positions of the two ends of the raw material billet 1 in the image and its actual scene.

[0138] The tilt detection unit 400 is used to detect the tilt status of the raw material billet 1 according to the mapping relationship.

[0139] In an optional embodiment of the present invention, such as Figure 8 As shown, the image acquisition unit 100 is an industrial camera 2, which is positioned directly opposite the elevator 3 to ensure that the images acquired by the industrial camera 2 always show both ends of the raw material billet 1.

[0140] The features and advantages of the raw material billet tilt detection device of the present invention are as follows:

[0141] During the lifting process of raw billet 1, it is necessary to detect whether it has tilted. However, due to the lack of effective detection methods, closed-loop control cannot be formed, and currently, this is mostly done through manual visual inspection. To address this problem, this invention employs an image processing device to acquire and process images of raw billet 1 during the lifting process, thereby detecting whether the raw billet 1 has actually tilted. This effectively improves the accuracy and efficiency of detection, providing a technical means for realizing unmanned automated production.

[0142] Implementation Method 3

[0143] The present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described method for detecting the tilt of raw billets.

[0144] Specifically, the computer device can be a computer terminal, a server, or a similar computing device.

[0145] Implementation Method 4

[0146] The present invention provides a computer-readable storage medium storing a computer program that performs the above-described method for detecting the tilt of raw billets.

[0147] Specifically, computer-readable storage media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable storage media does not include transient media, such as modulated data signals and carrier waves.

[0148] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0149] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0150] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0151] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0152] The above description is merely an illustrative embodiment of the present invention and is not intended to limit the scope of the invention. Any equivalent changes and modifications made by those skilled in the art without departing from the concept and principles of the present invention should fall within the scope of protection of the present invention.

Claims

1. A method for detecting the tilt of a raw billet, characterized in that, The method comprises the following steps: acquiring an image of the raw material blank to obtain the positions of the two ends of the raw material blank in the lifting process; detecting the pixel positions of the raw material blank in the image; calibrating the positions of the two ends of the raw material blank according to the pixel positions to obtain the mapping relationship between the positions of the two ends of the raw material blank in the image and in the actual scene; the calibration of the positions of the two ends of the raw material blank according to the pixel positions to obtain the mapping relationship between the positions of the two ends of the raw material blank in the image and in the actual scene comprises the following steps: during the lifting of the raw material blank, stopping the upward movement of the raw material blank after lifting the raw material blank for a preset time, and acquiring an image of the raw material blank in the stopped state; acquiring the upward movement distance of the raw material blank in each of the preset times; establishing the corresponding relationship between the image of the raw material blank in the stopped state and the upward movement of the raw material blank in the corresponding preset time; obtaining the mapping relationship between the image height of the two ends of the raw material blank in each image and the upward movement of the raw material blank in the corresponding preset time; detecting the tilting condition of the raw material blank according to the mapping relationship; the detection of the tilting condition of the raw material blank according to the mapping relationship comprises the following steps: during the lifting of the raw material blank, real-time acquisition of the image of the raw material blank, and obtaining the actual image height of the two ends of the raw material blank; finding the interval corresponding to the actual image height of the two ends of the raw material blank in the mapping relationship between the image height of the two ends of the raw material blank and the upward movement of the raw material blank in the corresponding preset time; respectively calculating the actual lifting height of the two ends of the raw material blank from the initial state; calculating the actual height difference of the two ends of the raw material blank; if the actual height difference is greater than a preset height difference threshold, the raw material blank is tilted; Wherein, L left is the actual lifting height of the first end of the raw material blank, L right is the actual lifting height of the second end of the raw material blank, h left is the image height of the first end of the raw material blank in the two-dimensional coordinate system, h right is the image height of the second end of the raw material blank; n is the number of times of obtaining images.

2. The raw material blank tilt detection method according to claim 1, characterized by, if the actual height difference is less than or equal to the preset height difference threshold, the raw material blank is not tilted; wherein the formula for calculating the actual lifting height of the two ends of the raw material blank from the initial state is: the detection of the pixel positions of the raw material blank in the image comprises the following steps: extracting the gray value of the red channel in the image to obtain a first gray image; performing contrast enhancement processing on the first gray image to obtain a first gray enhanced image; performing binaryzation processing on the first gray enhanced image to obtain a binaryzation image; 3. The raw material blank tilt detection method according to claim 2, characterized by, selecting an image region containing the raw material blank in the binaryzation image; extracting the image height of the two ends of the raw material blank in the image region. the selection of the image region containing the raw material blank in the binaryzation image comprises the following steps: traversing all image regions in the binaryzation image and calculating the area of each image region; respectively comparing the area of each image region with a preset determination value; if the area of the image region is greater than the preset determination value, the image region is the image region where the raw material blank is located; if the area of the image region is less than the preset determination value, the raw material blank does not exist in the image region.

4. The raw material blank tilt detection method according to claim 2, characterized by, The image height of the two end portions of the raw material blank in the image region includes: In a two-dimensional coordinate system, coordinates of all points of the raw material blank in the image region are obtained; All coordinate values of the raw material blank in the length direction are traversed, and a set of all coordinate values of the raw material blank in the height direction is obtained to determine the image height of the two end portions of the raw material blank.

5. The raw material blank tilt detection method according to claim 4, characterized by, The traversing of all coordinate values of the raw material blank in the length direction and the obtaining of the set of all coordinate values of the raw material blank in the height direction to determine the image height of the two end portions of the raw material blank includes: In the two-dimensional coordinate system, All coordinate values of the raw material blank in the length direction are traversed from small to large, and a first set of all coordinate values of the raw material blank in the height direction is obtained; An intermediate value of all coordinate values in the first set is obtained as the image height of the first end portion of the raw material blank; All coordinate values of the raw material blank in the length direction are traversed from large to small, and a second set of all coordinate values of the raw material blank in the height direction is obtained; 6. The raw material blank tilt detection method according to claim 1, wherein An intermediate value of all coordinate values in the second set is obtained as the image height of the second end portion of the raw material blank.

7. The raw material blank tilt detection method according to claim 6, wherein In the process of collecting the image of the raw material blank, the lifting process of the raw material blank by the elevator is collected by the industrial camera, and the two end portions of the raw material blank can always be displayed in the image.

8. A raw material billet tilt detection device, characterized in that, The industrial camera transmits the collected image to the server, and the server judges whether the raw material blank is tilted; if the raw material blank is tilted, the server generates an alarm signal. It includes: An image collection unit for collecting an image of a raw material blank to obtain positions of two end portions of the raw material blank in a lifting process; A raw material blank detection unit for detecting pixel positions of the raw material blank in the image; A mapping relationship acquisition unit for calibrating positions of the two end portions of the raw material blank according to the pixel positions to obtain a mapping relationship between the positions of the two end portions of the raw material blank in the image and in an actual scene; The mapping relationship acquisition unit is used in the lifting process of the raw material blank, The raw material blank is stopped after being lifted for a predetermined time, and an image of the raw material blank in a stopped state is obtained; The lifting distance of the raw material blank in each of the predetermined time is obtained; A corresponding relationship between the image of the raw material blank in the stopped state and the lifting of the raw material blank in the corresponding predetermined time is established; A mapping relationship between the image height of the two end portions of the raw material blank in each image and the lifting of the raw material blank in the corresponding predetermined time is obtained; An inclination detection unit for detecting the inclination of the raw material blank according to the mapping relationship; The inclination detection unit is used in the lifting process of the raw material blank, The image of the raw material blank is obtained in real time, and the actual image height of the two end portions of the raw material blank is obtained; The actual image height of the two end portions of the raw material blank is searched in the mapping relationship between the image height of the two end portions of the raw material blank and the lifting of the raw material blank in the corresponding predetermined time; The actual lifting height of the two end portions of the raw material blank from the initial state is calculated respectively; calculating an actual height difference of two end portions of the raw material blank; if the actual height difference is greater than a preset height difference threshold, the raw material blank is tilted; if the actual height difference is less than or equal to the preset height difference threshold, the raw material blank is not tilted; wherein a formula for calculating an actual lifting height of the two end portions of the raw material blank from an initial state is: wherein, L left is the actual lifting height of the first end of the raw material blank, L right is the actual lifting height of the second end of the raw material blank, h left is the image height of the first end of the raw material blank in the two-dimensional coordinate system, h right is the image height of the second end of the raw material blank; n is the number of times of obtaining images.

9. The raw material blank tilt detection apparatus according to claim 8, wherein The image acquisition unit is an industrial camera, and the industrial camera is arranged opposite the elevator to ensure that the two end portions of the raw material blank are always displayed in the image collected by the industrial camera.

10. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the raw material blank tilting detection method of any one of claims 1 to 7 when executing the computer program.

11. A computer readable storage medium, characterized in that, The computer readable storage medium stores a computer program for executing the raw material blank tilting detection method of any one of claims 1 to 7.

Images