Method, device, equipment and medium for positioning steel coil strip tail
By acquiring and verifying the tail coordinates and angular velocity data in the steel coil inspection images, the difficulty of tail detection was solved, high-precision tail positioning was achieved, and the accuracy and efficiency of the inspection system were improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA TELECOM CORP LTD
- Filing Date
- 2023-04-28
- Publication Date
- 2026-06-23
AI Technical Summary
In the detection of steel coil tails, existing technologies have difficulty effectively identifying tail characteristics, especially when the coil is obscured or pressed against the steel coil when it stops rotating. Furthermore, fog and temperature can lead to false detections, reducing machine operating efficiency.
By acquiring inspection images of the steel coil, the tail of the coil is identified and its coordinates and angular velocity are stored as the first data. Subsequent images are then acquired and stored as the second data. The accuracy of the data is verified, and the stationary position of the tail of the coil is determined using the second data.
It improves the accuracy of identifying the tail of the steel coil, ensures accurate positioning of the tail when the steel coil is stationary, and enhances the precision and efficiency of the detection system.
Smart Images
Figure CN116542923B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of steel coil tail detection, and more particularly to a method, apparatus, computer equipment, and readable storage medium for locating steel coil tails. Background Technology
[0002] In object detection, scene images are typically input directly, and convolutional detection networks are used to directly obtain the target. However, in industrial scenarios involving the detection of steel coil tails, while the rotation of the tail is relatively easy to detect, it becomes difficult to detect when it stops rotating because the tail is either obscured by the surrounding clamps or pressed against the coil. Furthermore, the steel coil tail is easily affected by fog, coil temperature, and drooping area during production, resulting in indistinct tail features and increasing the likelihood of false positives and negative detections, thus reducing machine operating efficiency. Summary of the Invention
[0003] This disclosure provides a method, apparatus, computer device, and readable storage medium for locating the tail of a steel coil, relating to the field of image recognition, which can improve the accuracy of tail recognition of steel coils.
[0004] This disclosure provides a method for locating the tail of a steel coil, comprising: acquiring a detection image of the steel coil; identifying the tail in the detection image of the steel coil; when the tail in the detection image of the steel coil is identified, storing the coordinates of the tail in the corresponding detection image of the steel coil and the angular velocity of the steel coil as first data; continuing to acquire and identify the tail in subsequent detection images of the steel coil, and storing the coordinates of the tail in the corresponding subsequent detection images of the steel coil and the angular velocity of the steel coil as second data; verifying the accuracy of the first data based on the second data; and when the first data is verified to be correct based on the second data, obtaining the position of the tail when the steel coil is stationary using the first data or the second data.
[0005] In one embodiment, continuing to acquire and identify the tail of the steel coil in subsequent detection images includes: continuing to acquire and identify the tail of the steel coil in subsequent detection images at N frame intervals, where N is an integer greater than 1.
[0006] In one embodiment, storing the coordinates of the tail of the steel coil in the corresponding subsequent detection image and the angular velocity of the steel coil as second data includes: when the tail in the detection image of the steel coil is identified, storing the number of N frame intervals of the corresponding subsequent detection image of the steel coil, the coordinates of the tail, and the angular velocity of the steel coil as second data.
[0007] In one embodiment, verifying the accuracy of the first data based on the second data includes: verifying whether the angle of the tail of the steel coil in the second data is accurate relative to the tail in the first data.
[0008] In one embodiment, verifying whether the angle of the tail of the steel coil in the second data relative to the tail in the first data is accurate includes: obtaining a first angle based on the coordinates of the tail of the steel coil in the second data and the coordinates of the tail in the first data; obtaining a second angle based on the number of frames of the detection image of the steel coil in the second data, the angular velocity of the steel coil, and the number of frames of the detection image of the steel coil in the first data, the angular velocity of the steel coil; and comparing whether the first angle and the second angle are within a threshold range.
[0009] In one embodiment, verifying the correctness of the first data based on the second data includes: when the second data includes multiple frames of subsequent detection images of the steel coil, the proportion of the tailed data of the detection images in the second data that verifies the correctness of the first data within a threshold range is greater than or equal to a first proportion.
[0010] In one embodiment, obtaining the position of the coil tail when it is stationary using the first data or the second data includes: when the detection system can determine the position of the coil tail when it is stationary based on the position of the coil tail when it is rotating, directly obtaining the position of the coil tail when it is stationary based on the position of the coil tail when it is moving in the first data or the second data; or when the detection system cannot determine the position of the coil tail when it is stationary based on the position of the coil tail when it is rotating, obtaining the position of the coil tail when it is stationary based on the angular velocity of the coil when it is moving and the deceleration of the coil in the first data or the second data.
[0011] This disclosure provides a positioning device for the tail of a steel coil, comprising: an acquisition unit for acquiring a detection image of the steel coil; an identification unit for identifying the tail in the detection image of the steel coil; a storage unit for storing the coordinates of the tail of the steel coil in the corresponding detection image and the angular velocity of the steel coil as first data when the tail of the steel coil in the detection image of the steel coil is identified; the identification unit is further configured to continue acquiring and identifying the tail in subsequent detection images of the steel coil, and storing the coordinates of the tail of the steel coil in the corresponding subsequent detection images and the angular velocity of the steel coil as second data; a verification unit for verifying the accuracy of the first data based on the second data; and the acquisition unit is further configured to acquire the position of the tail of the steel coil when it is stationary using the first data or the second data when the first data is verified to be correct based on the second data.
[0012] This disclosure provides a computer device, including: one or more processors; and a storage device configured to store one or more programs, which, when executed by the one or more processors, cause the one or more processors to perform the method as described in any of the above method embodiments.
[0013] This disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the above method embodiments.
[0014] The method for locating the tail of a steel coil disclosed in this application involves: acquiring a detection image of the steel coil; identifying the tail in the detection image; storing the coordinates of the tail and the angular velocity of the steel coil as first data when the tail is identified in the detection image; acquiring and identifying the tail in subsequent detection images of the steel coil, and storing the coordinates of the tail and the angular velocity of the steel coil as second data; verifying the accuracy of the first data based on the second data; and obtaining the position of the tail when the steel coil is stationary by using either the first or second data, thereby improving the accuracy of tail identification. Attached Figure Description
[0015] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0016] Figure 1 This is a flowchart of the positioning method for the tail of the steel coil provided in this embodiment of the disclosure;
[0017] Figure 2 This is a schematic diagram of the detection image during the positioning of the tail of a steel coil according to an embodiment of this application;
[0018] Figure 3 This is a flowchart illustrating a method for positioning the tail of a steel coil according to an embodiment of this application.
[0019] Figure 4 This is a schematic diagram of the structure of a positioning device for the tail of a steel coil provided in an embodiment of this disclosure;
[0020] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure. Detailed Implementation
[0021] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.
[0022] The following explains some of the technical terms used in this disclosure:
[0023] Steel coils, also known as rolled steel, are steel products formed by hot or cold pressing. They are used for easy storage and transportation, and for various processing (such as processing into steel plates or strips). After rolling, steel coils are sheared and coiled into coils of a specific diameter using a coiling machine. After coiling, the coils are either upright (core direction parallel to the ground) or horizontal (core direction perpendicular to the ground). Horizontal coils have a raised tail; only by accurately detecting and pressing down the tail can subsequent packaging proceed.
[0024] The tail section is the outer part of the steel coil that is cut off by the shearing machine. It refers to the outermost steel strip of the steel coil after cutting, similar to the tail of adhesive tape.
[0025] A frame is the smallest unit of image in animation, a single frame, equivalent to a single shot on film. A frame is a still image; consecutive frames create animation, such as television images. Frame rate, simply put, is the number of images transmitted per second, or how many times a graphics processor refreshes the screen per second, usually expressed in fps (Frames Per Second). Each frame is a still image; displaying frames rapidly and continuously creates the illusion of motion. A higher frame rate results in smoother, more realistic animation. The more frames per second (fps), the smoother the displayed motion. Industrial videos typically have around 20 frames per second, and image processing involves checking each frame individually.
[0026] Frame rate is the frequency (rate) at which bitmap images, measured in frames, appear continuously on a display screen. The term also applies to film and cameras, computer graphics, and motion capture systems. Frame rate can also be called frame frequency and is expressed in Hertz (Hz).
[0027] Figure 1 This is a flowchart of a method for positioning the tail of a steel coil provided in an embodiment of this disclosure. The method provided in this embodiment can be executed by any computer terminal or server with computing capabilities, or interactively executed by a terminal or server.
[0028] like Figure 1 As shown, the method provided in this disclosure embodiment may include the following steps.
[0029] In step S110, an inspection image of the steel coil is acquired.
[0030] In this step, the terminal or server can acquire an inspection image of the steel coil. In one embodiment, the inspection image of the steel coil can be acquired by a camera device, for example, by taking inspection images of the steel coil at a fixed frame rate T using a camera positioned on the inspection surface of the steel coil. Alternatively, the position of the center (center of rotation) of the steel coil in the inspection image captured by the camera can be determined by calibration.
[0031] In step S120, the tail of the steel coil in the detection image is identified.
[0032] In this step, the terminal or server identifies the tail of the steel coil in the detection image. In one embodiment, the terminal or server may be equipped with an artificial intelligence network recognition model, such as a convolutional neural network image recognition model, and the terminal or server identifies the tail of the steel coil in the detection image through the recognition model. In one embodiment, the terminal or server may identify images captured by the camera in sequence according to the frame rate, or it may extract images from the images captured by the camera for identification; this disclosure is not limited thereto.
[0033] In step S130, when the tail of the steel coil is identified in the detection image, the coordinates of the tail of the steel coil in the corresponding detection image and the angular velocity of the steel coil are stored as first data.
[0034] In this step, when the terminal or server identifies the tail of the steel coil in the detection image, it stores the coordinates of the tail of the steel coil in the corresponding detection image and the angular velocity of the steel coil as first data. In one embodiment, when the tail of the steel coil is first identified through the detection image, the coordinates of the tail and the angular velocity of the steel coil at that time can be stored as first data, and the first data can be numbered 1 or 0.
[0035] In step S140, the tail of the steel coil in the subsequent detection image is acquired and identified, and the coordinates of the tail of the steel coil in the corresponding subsequent detection image and the angular velocity of the steel coil are stored as second data.
[0036] In this step, the terminal or server continues to acquire and identify the tail of the steel coil in subsequent detection images, and stores the coordinates of the tail of the steel coil in the corresponding subsequent detection images and the angular velocity of the steel coil as second data. In one embodiment, continuing to acquire and identify the tail of the steel coil in subsequent detection images includes: continuing to acquire and identify the tail of the steel coil in subsequent detection images at N frame intervals, where N is an integer greater than 1. In one embodiment, N is required to satisfy the condition that the angular velocity of the steel coil multiplied by N and divided by the camera's frame rate is greater than a first angle, for example, greater than 30 degrees.
[0037] In one embodiment, storing the coordinates of the tail of the steel coil in the corresponding subsequent detection image and the angular velocity of the steel coil as second data includes: when the tail of the steel coil is identified in the detection image, storing the number of times the tail of the steel coil is detected in the corresponding subsequent detection image at an interval of N, the coordinates of the tail, and the angular velocity of the steel coil as second data. For example, the second data may include 5 sets of data, that is, the tail of the steel coil is successfully acquired 5 times in the subsequent detection images at an interval of N. Each set of data in the second data may include the number of times the tail of the steel coil is successfully acquired in the subsequent detection images at an interval of N. The detection images acquired at an interval of N do not necessarily detect the tail every time. For example, if the tail is detected in the third detection image acquired at an interval of N, then the third, N, the coordinates of the tail in the detection image, and the angular velocity of the steel coil are stored as the first set of data in the second data, and so on, until 5 sets of data are stored.
[0038] In step S150, the accuracy of the first data is verified based on the second data.
[0039] In this step, the terminal or server verifies the accuracy of the first data based on the second data. In one embodiment, verifying the accuracy of the first data based on the second data includes verifying whether the angle of the tail of the steel coil in the second data is accurate relative to the tail of the coil in the first data.
[0040] In one embodiment, verifying whether the angle of the tail of the steel coil in the second data relative to the tail in the first data is accurate includes: obtaining a first angle based on the coordinates of the tail of the steel coil in the second data and the coordinates of the tail in the first data; obtaining a second angle based on the number of frames and the angular velocity of the steel coil in the detection image of the steel coil in the second data and the number of frames and the angular velocity of the steel coil in the detection image of the steel coil in the first data; and comparing whether the first angle and the second angle are within a threshold range. For example, when the second data includes a set of data on the tail in subsequent detection images of the steel coil acquired at N frame intervals and identified, and when the tail is detected in the third detection image acquired at N intervals, the first angle centered on the center of the steel coil for the two tails is calculated based on the coordinates of the tail in the first data and the coordinates of the tail in the second data. Then, the second angle centered on the center of the steel coil for the two tails is calculated according to the following formula (1):
[0041] α=(v0+v n (n-n0)N / 2T (1)
[0042] Where α is the second angle, v0 is the angular velocity of the steel coil in the first data, and v nThe second set of data represents the angular velocity of the steel coil. N represents the number of detection images acquired at N intervals, n represents the nth detection image acquired at N intervals where the tail of the coil was detected, n0 is 0, and T is the camera frame rate. For example, if the first and second angles are within a threshold range (e.g., 2 degrees), the angle of the tail of the steel coil in the second set of data relative to the tail in the first set of data is considered accurate. When the second set of data includes multiple sets of data, the verification is performed sequentially.
[0043] In step S160, when verifying the correctness of the first data based on the second data, the position of the tail of the steel coil when it is stationary is obtained through the first data or the second data.
[0044] In this step, when the terminal or server verifies the correctness of the first data based on the second data, it obtains the position of the tail of the steel coil when it is stationary through the first data or the second data.
[0045] In one embodiment, verifying the correctness of the first data based on the second data includes: when the second data includes multiple frames of subsequent detection images of the steel coil, the proportion of the tailed data of the detection images in the second data that verifies the correctness of the first data within a threshold range is greater than or equal to a first proportion (e.g., 80%). For example, if the second data includes 5 sets of data, and 4 sets of data respectively verify that the first data is within the threshold range, then it is considered that the first data is correct based on the second data.
[0046] In one embodiment, obtaining the position of the coil tail when stationary using the first data or the second data includes: when the detection system can determine the position of the coil tail when stationary based on the position of the coil tail during rotation, directly obtaining the position of the coil tail when stationary based on the position of the coil tail during movement in the first data or the second data; or when the detection system cannot determine the position of the coil tail when stationary based on the position of the coil tail during rotation, obtaining the position of the coil tail when stationary based on the angular velocity and deceleration of the coil during movement in the first data or the second data. For example, some coil tail positioning systems, after knowing the current rotational speed and coordinates of the coil tail, can directly output the coordinates of the coil tail when it stops, thus obtaining the position of the coil tail when stationary based on the position of the coil tail during movement in the first data or the second data.
[0047] For example, a positioning system for the tail of a steel coil, after knowing the current rotational speed and coordinates of the tail, cannot directly output the coordinates of the tail when it stops. Instead, it can obtain the position of the tail when the steel coil is stationary by using the angular velocity and deceleration of the steel coil during its movement as described in the first or second data. Specifically, taking the first data as an example, the angle between the tail when it stops and the tail in the first data can be obtained using the following formula (2), thereby determining the position of the tail when it stops:
[0048]
[0049] Where β is the angle between the coil tail at the stopping position and the coil tail in the first data, v0 is the angular velocity of the coil in the first data, a is the angular deceleration of the coil, and v n ω is the angular velocity of the steel coil in the second set of data, N is the detection image acquired at intervals of N, n is the detection image acquired at intervals of N in the nth time that the tail of the belt was detected, n0 is 0, and T is the camera frame rate.
[0050] Figure 1 The method for locating the tail of a steel coil, as shown, involves acquiring a detection image of the steel coil; identifying the tail in the detection image; storing the coordinates of the tail and the angular velocity of the steel coil as first data when the tail is identified; acquiring and identifying the tail in subsequent detection images of the steel coil, and storing the coordinates of the tail and the angular velocity of the steel coil as second data; verifying the accuracy of the first data based on the second data; and obtaining the position of the tail when the steel coil is stationary using either the first or second data. This method improves the accuracy of tail identification, thereby achieving the detection and positioning of the tail of the steel coil.
[0051] The positioning method disclosed herein will be explained in detail below with specific examples:
[0052] Figure 2 This is a schematic diagram of the detection image during the positioning of the tail of a steel coil according to an embodiment of this application.
[0053] refer to Figure 2 Before inspection, the center O of the steel coil 201 is calibrated. After the center O is calibrated, the center O of the steel coil in the inspection image acquired by the imaging device becomes known data.
[0054] refer to Figure 2The values 1-6 represent the positions of the tail of the steel coil in different detection images. For example, 1 can represent the position of the tail of the steel coil in the first detected data. 2-6 (5 groups in total) can represent, for example, 5 groups of tail positions in the second data, obtained at intervals of N in the detection images of the steel coil. The interval N is required to conform to the ratio of the angular velocity of the steel coil multiplied by N and divided by the camera's frame rate (…). Figure 2 The angle between points 1 and 2 about the center O is greater than the first angle, for example, greater than 30 degrees.
[0055] refer to Figure 2 After acquiring the first data of the tail 1 in the detection image of the steel coil, the coordinates of the tail in the corresponding subsequent detection image of the steel coil and the second data of the angular velocity of the steel coil are used. Figure 2 (5 groups in total, 2-6) Verify the position of the tail 1 in the first data. If no less than 4 out of the 5 groups are within the threshold range, the position of the tail 1 in the first data is determined to be correct. If the verification is incorrect, the detection is restarted until the verification is passed.
[0056] After confirming that the position of the tail 1 in the first data is correct, the position of the tail of the steel coil when it is at rest can be determined by the following two methods:
[0057] (1) In the actual scenario, the steel coil factory calculates using physical modeling, so it can output the angle from the current moment to the machine stopping rotation state. It can take the confirmed tail position (e.g., the position of tail 1 in the first data) as the starting point and rotate by a known angle to locate the final tail stopping direction. Therefore, it can directly obtain the position of the tail when the steel coil is stationary.
[0058] (2) If there is no machine output angle, the characteristics of uniform deceleration motion can be used to calculate the angle β that the belt tail will rotate from the currently confirmed position to the final stop of the belt tail. The formula is as follows, which can then determine the final stop position of the belt tail.
[0059]
[0060] Figure 3 This is a flowchart illustrating a method for positioning the tail of a steel coil according to an embodiment of this application.
[0061] refer to Figure 3 The positioning method for the tail of the steel coil in this application may include the following specific scenarios:
[0062] Scenario 1:
[0063] Step 1: Determine the status flag of the steel coil inspection. When a new steel coil inspection begins, the flag is reset to 0. When the tail position of the strip to be inspected is detected for the first time, the flag is set to 1. When the tail position of the steel coil inspection is confirmed, the flag is set to 2.
[0064] Step 2: Maintain the calculated frame interval N and perform band tail detection. If a band tail to be checked is detected and the status flag is 0, add the detection result to the first item in the dictionary dict{(n*N):(x,y,v)}; where N is the determined frame interval, n is the number of frame intervals since the first detected band tail frame, x is the x-coordinate of the detected band tail, y is the y-coordinate, and v is the angular velocity transmitted by the system at the current moment.
[0065] Step 3: Simultaneously set the status flag to 1.
[0066] Scenario 2:
[0067] Step 1: Determine the status flag. When a new steel coil is started for inspection, the flag is reset to 0. When the tail position of the strip to be inspected is detected for the first time, the flag is set to 1. When the tail position of the steel coil is confirmed for inspection, the flag is set to 2.
[0068] Step 2: Maintain the calculated frame interval N and perform band tail detection. If a band tail to be checked is detected, and the curling state flag is 1, add the detection result to the last item in the dictionary dict{(n*N):(x,y,v)} list.
[0069] Step 3: Determine if the length of the dictionary list (dict) is greater than 5. If it is less than 5, continue to wait for the subsequent test results.
[0070] Scenario 3:
[0071] Step 1: Determine the status flag. When a new steel coil is started for inspection, the flag is reset to 0. When the tail position of the strip to be inspected is detected for the first time, the flag is set to 1. When the tail position of the steel coil is confirmed for inspection, the flag is set to 2.
[0072] Step 2: Maintain the calculated frame interval N and perform band tail detection. If a band tail to be checked is detected, and the curling state flag is 1, add the detection result to the last item in the list dict{(n*N):(x,y,v)}.
[0073] Step 3: Check if the length of the dict list is greater than 5. If it is greater than 5, verify the result.
[0074] Step 4: Begin calculating the angle of the band tail relative to the center of the circle in each image frame. Starting from the first band tail, calculate the angles that the other 5 points should appear at, as shown in formula (1). Since it is a uniformly decelerated motion, the angle difference is α:
[0075] α=(v0+v n (n-n0)N / 2T (1)
[0076] Where n0 is the key value of the first point in the current list. If more than 80% of the remaining 5 points in the list have an error of less than 2° from the calculated direction, it is determined that the current first group of tail detection is correct, and the curling status flag is set to 2.
[0077] Step 5: Using the confirmed tail position as the starting point and the corresponding machine rotational angular velocity, the final stopping position of the tail can be calculated and located.
[0078] Scenario 4:
[0079] Step 1: Determine the status flag. When a new steel coil is started for inspection, the flag is reset to 0. When the tail position of the strip to be inspected is detected for the first time, the flag is set to 1. When the tail position of the steel coil is confirmed for inspection, the flag is set to 2.
[0080] Step 2: Maintain the calculated frame interval N and perform band tail detection. If a band tail to be checked is detected, and the curling state flag is 1, add the detection result to the last item in the list dict{(n*N):(x,y,v)}.
[0081] Step 3: Check if the length of the dict list is greater than 5. If it is greater than 5, verify the result.
[0082] Step 4: Begin calculating the angle of the band tail relative to the center of the circle in each image frame. Starting with the first element, calculate the angles that the other 5 points should appear at. If for the remaining 5 points in the list, fewer than four have an error of less than 2° with the calculated direction, the first set of data is considered a false detection, and the first set is deleted from the list, awaiting subsequent input.
[0083] Scenario 5:
[0084] Step 1: Determine the status flag. When a new steel coil is started for inspection, the flag is reset to 0. When the tail position of the strip to be inspected is detected for the first time, the flag is set to 1. When the tail position of the steel coil is confirmed for inspection, the flag is set to 2.
[0085] Step 2: Maintain the calculated frame interval N and perform band tail detection. If a band tail to be verified is detected, and the curling state flag is 2, the detected target to be verified is ignored.
[0086] Figure 4 This is a schematic diagram of the structure of a positioning device for the tail of a steel coil provided in an embodiment of this disclosure.
[0087] like Figure 4 As shown, the positioning device 400 for the tail of the steel coil provided in this embodiment may include:
[0088] Acquisition unit 410 is used to acquire the detection image of the steel coil;
[0089] The identification unit 420 is used to identify the tail in the detection image of the steel coil;
[0090] The storage unit 430 is used to store the coordinates of the tail of the steel coil in the corresponding detection image and the angular velocity of the steel coil as first data when the tail of the steel coil is identified in the detection image of the steel coil.
[0091] The identification unit 410 is further configured to continue to acquire and identify the tail in the subsequent detection image of the steel coil, and store the coordinates of the tail in the corresponding subsequent detection image of the steel coil and the angular velocity of the steel coil as second data.
[0092] Verification unit 440 is used to verify the accuracy of the first data based on the second data;
[0093] The acquisition unit 410 is further configured to acquire the position of the tail of the steel coil when it is stationary by means of the first data or the second data when verifying the correctness of the first data based on the second data.
[0094] like Figure 4 The steel coil tail positioning device 400 shown includes: an acquisition unit for acquiring a detection image of the steel coil; an identification unit for identifying the tail in the detection image of the steel coil; a storage unit for storing the coordinates of the tail and the angular velocity of the steel coil as first data when the tail in the detection image of the steel coil is identified; the identification unit is further used to acquire and identify the tail in subsequent detection images of the steel coil, and store the coordinates of the tail and the angular velocity of the steel coil as second data; a verification unit for verifying the accuracy of the first data based on the second data; and the acquisition unit is further used to acquire the position of the tail of the steel coil when it is stationary using the first data or the second data when the first data is verified to be correct based on the second data, which can improve the accuracy of tail identification of the steel coil, thereby realizing the detection and positioning of the tail of the steel coil.
[0095] In one embodiment, the identification unit 420 is further configured to continue acquiring and identifying the tail in subsequent detection images of the steel coil at N frame intervals, where N is an integer greater than 1.
[0096] In one embodiment, the identification unit 420 is further configured to, when identifying the tail in the detection image of the steel coil, store the number of N frame intervals of the corresponding subsequent detection image of the steel coil, the coordinates of the tail, and the angular velocity of the steel coil as second data.
[0097] In one embodiment, the verification unit 440 is further configured to verify whether the angle of the tail of the steel coil in the second data relative to the tail in the first data is accurate.
[0098] In one embodiment, the verification unit 440 is further configured to obtain a first angle based on the coordinates of the tail of the steel coil in the second data and the coordinates of the tail in the first data; obtain a second angle based on the number of frames of the detection image of the steel coil in the second data, the angular velocity of the steel coil, and the number of frames of the detection image of the steel coil in the first data, the angular velocity of the steel coil; and compare whether the first angle and the second angle are within a threshold range.
[0099] In one embodiment, the verification unit 440 is further configured to verify that the proportion of the first data within a threshold range is greater than or equal to a first proportion when the second data includes multiple frames of subsequent detection images of the steel coil.
[0100] In one embodiment, the acquisition unit 410 is further configured to, when the detection system has the capability to determine the tail position of the steel coil when it is stationary based on the tail position of the steel coil during rotation, directly acquire the tail position of the steel coil when it is stationary based on the tail position of the steel coil during movement in the first data or the second data; or when the detection system does not have the capability to determine the tail position of the steel coil when it is stationary based on the tail position of the steel coil during rotation, acquire the tail position of the steel coil when it is stationary based on the angular velocity of the steel coil during movement and the deceleration of the steel coil in the first data or the second data.
[0101] See Figure 5 , Figure 5 This is a schematic diagram of the structure of a computer device 500 provided in an embodiment of this disclosure. Figure 5 As shown, the computer device in this embodiment may include one or more processors 501, a memory 502, and an input / output interface 503. The processor 501, memory 502, and input / output interface 503 are connected via a bus 504. The memory 502 stores a computer program, which includes program instructions. The input / output interface 503 receives and outputs data, such as for data interaction between the host machine and the computer device, or for data interaction between various virtual machines within the host machine. The processor 501 executes the program instructions stored in the memory 502.
[0102] The processor 501 can perform the following operations:
[0103] Acquire a detection image of the steel coil; identify the tail of the coil in the detection image; when the tail of the coil is identified, store the coordinates of the tail of the coil in the corresponding detection image and the angular velocity of the coil as first data; continue to acquire and identify the tail of the coil in subsequent detection images, and store the coordinates of the tail of the coil in the corresponding subsequent detection images and the angular velocity of the coil as second data; verify the accuracy of the first data based on the second data; when the first data is verified to be correct based on the second data, obtain the position of the tail of the coil when it is stationary using the first data or the second data.
[0104] In some feasible implementations, the processor 501 may be a central processing unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.
[0105] The memory 502 may include read-only memory and random access memory, and provides instructions and data to the processor 501 and the input / output interface 503. A portion of the memory 502 may also include non-volatile random access memory. For example, the memory 502 may also store device type information.
[0106] In practice, the computer device can execute the implementation methods provided by the steps in the above embodiments through its built-in functional modules. For details, please refer to the implementation methods provided by the steps in the above embodiments, which will not be repeated here.
[0107] This disclosure provides a computer device including a processor, an input / output interface, and a memory. The processor retrieves a computer program from the memory and executes the steps of the method shown in the above embodiments to perform a transmission operation.
[0108] This disclosure also provides a computer-readable storage medium storing a computer program adapted to be loaded by a processor and execute the methods provided in the steps of the above embodiments. Specific implementations of the steps in the above embodiments can be found therein and will not be repeated here. Furthermore, the beneficial effects of using the same method will not be repeated here either. For technical details not disclosed in the embodiments of the computer-readable storage medium involved in this disclosure, please refer to the description of the method embodiments of this disclosure. As an example, the computer program can be deployed to execute on a single computer device, or on multiple computer devices located in one location, or on multiple computer devices distributed across multiple locations and interconnected via a communication network.
[0109] The computer-readable storage medium can be the apparatus provided in any of the foregoing embodiments or the internal storage unit of the computer device, such as the hard disk or memory of the computer device. The computer-readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., provided on the computer device. Furthermore, the computer-readable storage medium can include both internal storage units and external storage devices of the computer device. The computer-readable storage medium is used to store the computer program and other programs and data required by the computer device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.
[0110] This disclosure also provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various alternative embodiments described above.
[0111] The terms "first," "second," etc., used in the specification, claims, and drawings of this disclosure are used to distinguish different objects, not to describe a specific order. Furthermore, the term "comprising," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or modules, but may optionally include steps or modules not listed, or may optionally include other step units inherent to these processes, methods, apparatuses, products, or devices.
[0112] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.
[0113] The methods and related apparatuses provided in this disclosure are described with reference to the method flowcharts and / or structural diagrams provided in this disclosure. Specifically, each block of the method flowchart and / or structural diagram, as well as combinations of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions are provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable transmission device to create a machine, such that the instructions, which execute via the processor of the computer or other programmable transmission device, generate instructions for implementing the process. Figure 1 A schematic diagram of one or more processes and / or structures. Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable transmission 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 A schematic diagram of one or more processes and / or structures. Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable transmission device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 A process or multiple processes and / or structures illustrate the steps of the functions specified in one or more boxes.
[0114] The above-disclosed embodiments are merely preferred embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Therefore, any equivalent variations made in accordance with the claims of this disclosure shall still fall within the scope of this disclosure.
Claims
1. A method for positioning the tail of a steel coil, characterized in that, include: Obtain inspection images of the steel coil; Identify the tail in the detection image of the steel coil; When the tail of the steel coil is identified in the detection image, the coordinates of the tail of the steel coil in the corresponding detection image and the angular velocity of the steel coil are stored as first data. Continue to acquire and identify the tail in the subsequent detection image of the steel coil, and store the coordinates of the tail in the corresponding subsequent detection image of the steel coil and the angular velocity of the steel coil as second data; Verify the accuracy of the first data based on the second data; When verifying the correctness of the first data based on the second data, the position of the tail of the steel coil when it is stationary is obtained through the first data or the second data. The verification of whether the angle of the tail of the steel coil in the second data relative to the tail in the first data is accurate includes: obtaining a first angle based on the coordinates of the tail of the steel coil in the second data and the coordinates of the tail in the first data; obtaining a second angle based on the number of frames and the angular velocity of the steel coil in the detection image of the steel coil in the second data and the number of frames and the angular velocity of the steel coil in the detection image of the steel coil in the first data; and comparing whether the first angle and the second angle are within a threshold range. Calculate the second angle centered on the center of the steel coil for both tails using the following formula: ； in, For the second angle, It is the angular velocity of the steel coil in the first data point. It is the angular velocity of the steel coil in the second data point. These are detection images acquired at intervals of N. It is the first The detection images acquired at N intervals detected a tail. It is 0. It's the camera frame rate; The method of obtaining the position of the tail of the steel coil when it is stationary through the first data or the second data includes: when the detection system can determine the position of the tail of the steel coil when it is stationary based on the position of the tail when the steel coil is rotating, the position of the tail of the steel coil when it is stationary is obtained directly based on the position of the tail when the steel coil is moving in the first data or the second data; or when the detection system cannot determine the position of the tail of the steel coil when it is stationary based on the position of the tail when the steel coil is rotating, the position of the tail of the steel coil when it is stationary is obtained based on the angular velocity and the deceleration of the steel coil when it is moving in the first data or the second data. The angle between the tail-stopping position and the tail of the first data is obtained using the following formula, thereby determining the position of the tail-stopping position: ； in, The angle between the end of the data and the end of the first data at the end of the data band stopping position. It is the angular deceleration of the steel coil.
2. The method according to claim 1, characterized in that, Continuing to acquire and identify the tail in subsequent detection images of the steel coil includes: The tail of the steel coil is acquired and identified in subsequent detection images at N frame intervals, where N is an integer greater than 1.
3. The method according to claim 2, characterized in that, Storing the tailed coordinates of the corresponding subsequent detection image of the steel coil and the angular velocity of the steel coil as second data includes: When the tail of the steel coil is identified in the detection image, the number of times the corresponding subsequent detection images of the steel coil are N frame intervals, the coordinates of the tail, and the angular velocity of the steel coil are stored as second data.
4. The method according to claim 1, characterized in that, Verifying the accuracy of the first data based on the second data includes: Verify whether the angle of the tail of the steel coil in the second data relative to the tail in the first data is accurate.
5. The method according to claim 1, characterized in that, Verifying the correctness of the first data based on the second data includes: When the second data includes multiple frames of subsequent detection images of the steel coil, the tailed data of the detection images in the second data verifies that the correct proportion of the first data within the threshold range is greater than or equal to the first proportion.
6. A positioning device for the tail of a steel coil, characterized in that, include: The acquisition unit is used to acquire the detection image of the steel coil; The identification unit is used to identify the tail in the detection image of the steel coil; The storage unit is used to store the coordinates of the tail of the steel coil in the corresponding detection image and the angular velocity of the steel coil as first data when the tail of the steel coil is identified in the detection image. The identification unit is further configured to continue to acquire and identify the tail in the subsequent detection image of the steel coil, and store the coordinates of the tail in the corresponding subsequent detection image of the steel coil and the angular velocity of the steel coil as second data. Verification unit, used to verify the accuracy of the first data based on the second data; The acquisition unit is further configured to acquire the position of the tail of the steel coil when it is stationary by means of the first data or the second data when verifying the correctness of the first data based on the second data. The verification unit is further configured to obtain a first angle based on the coordinates of the tail of the steel coil in the second data and the coordinates of the tail in the first data; obtain a second angle based on the number of frames and the angular velocity of the steel coil in the detection image of the steel coil in the second data and the number of frames and the angular velocity of the steel coil in the detection image of the steel coil in the first data; and compare whether the first angle and the second angle are within a threshold range. The verification unit is also used to calculate the second angle centered on the center of the steel coil for the two tailed sections according to the following formula: ； in, For the second angle, It is the angular velocity of the steel coil in the first data point. It is the angular velocity of the steel coil in the second data point. These are detection images acquired at intervals of N. It is the first The detection images acquired at N intervals detected a tail. It is 0. It's the camera frame rate; The acquisition unit is further configured to, when the detection system can determine the tail position of the steel coil when it is stationary based on the tail position of the steel coil during rotation, directly acquire the tail position of the steel coil when it is stationary based on the tail position of the steel coil during movement in the first data or the second data; or, when the detection system cannot determine the tail position of the steel coil when it is stationary based on the tail position of the steel coil during rotation, acquire the tail position of the steel coil when it is stationary based on the angular velocity of the steel coil during movement and the deceleration of the steel coil in the first data or the second data. The acquisition unit is further configured to obtain the angle between the tail-ending position and the tail of the first data using the following formula, thereby determining the position at the tail-ending position: ； in, The angle between the end of the data and the end of the first data at the end of the data band stopping position. It is the angular deceleration of the steel coil.
7. A computer device, characterized in that, include: One or more processors; A storage device configured to store one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 5.
8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 5.