Aluminum bar quality inspection-oriented profile bending detection method, system and device

Abstract

The application relates to a profile bending detection method, system and equipment for aluminum bar quality detection. The method comprises the following steps: in response to receiving a demolding completion signal sent by a demolding assembly, acquiring a first image of each aluminum bar; in response to receiving a transmission signal, acquiring multiple second images of each aluminum bar; determining a preliminary screening aluminum bar from the multiple aluminum bars according to a profile difference index of the aluminum bar; determining a displacement mutation index and a displacement change rate of each feature point in each frame based on the position difference of each feature point in the second images of adjacent frames in the second image sequence corresponding to the preliminary screening aluminum bar; determining a surface fluctuation index of the preliminary screening aluminum bar based on the displacement mutation index and the displacement change rate; and performing bending analysis on the preliminary screening aluminum bar based on the surface fluctuation index to obtain an analysis result. By using the method, whether the aluminum bar has undergone continuous deformation can be judged through time sequence images, and an aluminum bar with a real bending defect can be screened out for straightening.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a contour bending detection method, system, and equipment for aluminum bar quality inspection. Background Art

[0002] Aluminum rods are the "backbone" of modern industry. Their quality directly determines the performance and safety of end products, from precision aerospace components to building support structures, from lightweight chassis for new energy vehicles to heat dissipation modules for electronic products. The quality inspection process for aluminum rods, like the calibration of an instrument, ensures that the chemical composition, mechanical properties, and internal structure of each rod meet standards through rigorous quality inspection procedures. This prevents production accidents and economic losses caused by quality risks and ensures the reliability of aluminum rod products throughout their entire lifecycle, from raw materials to finished products. In the traditional quality inspection process for aluminum rod production, cast aluminum rods, regardless of whether they are bent or not, are sent to straightening equipment for processing. This one-size-fits-all approach, while ensuring basic product quality, inadvertently consumes a significant amount of time and costs.

[0003] In the aluminum bar production line, production efficiency and product quality are crucial. Traditional aluminum bar production processes uniformly straighten all aluminum bars to prevent bending due to cooling after casting. When an aluminum bar bends, the contour changes often exhibit a large, continuous deformation along the axial direction. This means that the edge of one side will exhibit a large-scale offset, extending from a local area to the entire bar. Local contour changes are often caused by interfering factors such as surface stains and oxide film shedding, and are usually small-scale discontinuous anomalies. The uniform straightening of all aluminum bars does not distinguish between actually bent aluminum bars and those with irregular, sudden changes in the amplitude of the bumps due to oxide film shedding. This causes unbent aluminum bars to undergo unnecessary process steps, resulting in loss of time and equipment. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a contour bending detection method, system and equipment for aluminum bar quality inspection. The technical solutions adopted are as follows:

[0005] In a first aspect, a contour bending detection method for aluminum bar quality inspection is provided, the method comprising:

[0006] In response to receiving a demolding completion signal from the demolding assembly, a first image of each aluminum bar is acquired; in response to receiving a transmission signal, multiple frames of second images of each aluminum bar are acquired; the transmission signal indicates that the aluminum bar is in the process of being transferred from the demolding assembly to the straightening assembly;

[0007] Determining the preliminarily screened aluminum bars from the plurality of aluminum bars according to an aluminum bar contour difference index obtained by analyzing the offset between each edge contour point of the first image and the second image of the first frame;

[0008] For a single pre-screened aluminum bar, the displacement mutation index and displacement change rate of each feature point in each frame are determined based on the positional differences of each feature point in the second images of adjacent frames in the second image sequence corresponding to the pre-screened aluminum bar. The displacement mutation index indicates whether the position of each feature point has changed suddenly, and the displacement change rate indicates the magnitude of the position change of each feature point. The feature points of adjacent frames correspond one to one, and each feature point is obtained using a corner point detection algorithm.

[0009] Determining a surface fluctuation index of the primary screening aluminum rod based on the displacement mutation index and the displacement change rate;

[0010] The bending analysis of the primary screening aluminum bars was carried out based on the surface fluctuation index to obtain the analysis results.

[0011] Optionally, the profile difference index is obtained according to the following steps:

[0012] Extracting multiple edge contour points of the first image and the first frame second image based on the Canny operator;

[0013] determining, based on coordinate differences between a plurality of edge contour points of the first image and a plurality of edge contour points of the first frame second image, a radial offset between each edge contour point of the first image and the first frame second image, and determining an edge contour point having a radial offset greater than a preset offset threshold as an abnormal contour point;

[0014] The profile difference index is determined based on the length of the abnormal curve formed by connecting all abnormal profile points, the length of the aluminum rod, and the sum of the radial offsets of all abnormal profile points.

[0015] Optionally, determining the profile difference index based on the length of the abnormal curve formed by connecting all abnormal profile points, the length of the aluminum bar, and the sum of the radial offsets of all abnormal profile points includes:

[0016] The contour difference index is determined based on the product of the line segment ratio and the anomaly ratio; the line segment ratio indicates the ratio of the length of the abnormal curve to the length of the aluminum rod, the anomaly ratio indicates the ratio of the sum of the radial offsets of all abnormal contour points to the number of offsets, and the offset number indicates the product of the total number of abnormal contour points and the offset threshold.

[0017] Optionally, based on the position difference of each feature point in the second image of adjacent frames in the second image sequence corresponding to the primary screening aluminum bar, determining the displacement mutation index and displacement change rate of each feature point in each frame includes:

[0018] Based on the absolute difference between the first vibration displacement and the second vibration displacement and the first vibration displacement, determining the displacement change rate of each feature point in each frame; the first vibration displacement indicates the vibration displacement of each feature point in the second image of the first target frame, the first vibration displacement is calculated based on the Euclidean distance between the coordinates of each feature point in the first target frame and the average value of its coordinates in all frames, and the first target frame indicates a frame that is closer to the front among adjacent frames; the second vibration displacement indicates the vibration displacement of each feature point in the second image of the second target frame, the second vibration displacement is calculated based on the Euclidean distance between the coordinates of each feature point in the second target frame and the average value of its coordinates in all frames, and the second target frame indicates a frame that is closer to the back among adjacent frames;

[0019] Based on the absolute difference between the first vibration displacement and the second vibration displacement, a displacement mutation index of each feature point in each frame is determined.

[0020] Optionally, determining the displacement change rate of each feature point in each frame based on the absolute difference between the first vibration displacement and the second vibration displacement and the first vibration displacement includes:

[0021] For a single feature point, determine the displacement change rate of the feature point in each frame based on the ratio of the absolute difference between the first vibration displacement of the feature point and the second vibration displacement of the feature point to the first vibration displacement of the feature point;

[0022] The ratio of the absolute difference between the first vibration displacement and the second vibration displacement of each feature point in each frame to the first vibration displacement is calculated to determine the displacement change rate of each feature point in each frame.

[0023] Optionally, determining the displacement mutation index of each feature point in each frame based on the absolute difference between the first vibration displacement and the second vibration displacement includes:

[0024] For a single feature point, if the absolute difference between the first vibration displacement and the second vibration displacement is greater than a preset mutation index, the displacement mutation index of the feature point in the second target frame is determined to be one; if not, the displacement mutation index of the feature point in the second target frame is determined to be zero;

[0025] The absolute difference between the first vibration displacement and the second vibration displacement of each feature point in each frame is calculated to obtain the displacement mutation index of each feature point in each frame.

[0026] Optionally, determining the surface fluctuation index of the primary screening aluminum bar based on the displacement mutation index and the displacement change rate includes:

[0027] The surface fluctuation index of the initially screened aluminum bar is determined based on the displacement mutation index of each feature point in each frame in the second image sequence, the displacement change rate of each feature point in each frame in the second image sequence, the number of feature points in a single frame of the second image, and the valid frame number; the valid frame number indicates the number of second images in the second image sequence minus one.

[0028] Optionally, determining the surface fluctuation index of the pre-screened aluminum bar based on the displacement mutation index of each feature point in each frame in the second image sequence, the displacement change rate of each feature point in each frame in the second image sequence, the number of feature points in a single-frame second image, and the number of valid frames includes:

[0029] The surface fluctuation index of the initially screened aluminum rod is determined based on the ratio of the sum of the displacements to the sum of the characteristic points; the sum of the displacements indicates the sum of the products of the displacement mutation index of each characteristic point in each frame of the second image sequence and the displacement change rate of each characteristic point in each frame of the second image sequence, and the sum of the characteristic points indicates the product of the number of characteristic points in a single frame of the second image and the number of valid frames.

[0030] In a second aspect, a contour bending detection system for aluminum bar quality inspection is provided, the system comprising:

[0031] an acquisition module, configured to acquire a first image of each aluminum bar in response to receiving a demolding completion signal from the demolding assembly; and acquire multiple frames of second images of each aluminum bar in response to receiving a transmission signal, wherein the transmission signal indicates that the aluminum bar is in the process of being transferred from the demolding assembly to the straightening assembly;

[0032] A first determination module is configured to determine a preliminarily screened aluminum bar from a plurality of aluminum bars based on a contour difference index of the aluminum bars, wherein the contour difference index is obtained by analyzing an offset between each edge contour point of the first image of the aluminum bar and the second image of the first frame;

[0033] The second determination module is configured to determine, for a single pre-screened aluminum bar, a displacement mutation index and a displacement change rate of each feature point in each frame based on the positional differences of each feature point in adjacent frames of the second image sequence corresponding to the pre-screened aluminum bar; the displacement mutation index indicates whether the position of each feature point has a mutation, and the displacement change rate indicates the magnitude of the position change of each feature point; the feature points of adjacent frames correspond one to one, and each feature point is obtained using a corner detection algorithm;

[0034] a third determining module, configured to determine a surface fluctuation index of the primary screening aluminum rod based on the displacement mutation index and the displacement change rate;

[0035] The analysis module is used to perform bending analysis on the primary screening aluminum bars based on the surface fluctuation index to obtain analysis results.

[0036] In a third aspect, a contour bending detection electronic device for aluminum bar quality inspection is provided, comprising a memory, a processor, and a computer program stored in the memory and for running on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0037] On the basis of conforming to the common sense in this field, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present invention.

[0038] The present application has the following beneficial effects: the surface fluctuation index is determined by utilizing the displacement mutation index and displacement change rate of each feature point in the second image sequence of the aluminum bar, the periodic changes of the aluminum bar during transportation are analyzed in combination with the second image sequence, and accurate judgment is made based on the difference in physical properties between the bent aluminum bar and the interference, so as to identify the bending area of ​​the aluminum bar, compare the irregular fluctuations generated by the bent aluminum bar and the interference, judge whether the aluminum bar has undergone continuous deformation, screen out aluminum bars with real bending defects, and allow qualified products to skip the straightening process, thereby ensuring quality while improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0040] Figure 1 A flowchart of a contour bending detection method for aluminum bar quality inspection provided by one embodiment of the present application;

[0041] Figure 2 A schematic diagram of aluminum bar transmission for a contour bending detection method for aluminum bar quality inspection provided by one embodiment of the present application;

[0042] Figure 3 A schematic structural diagram of a contour bending detection system for aluminum bar quality inspection provided by one embodiment of the present application;

[0043] Figure 4 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0044] To further illustrate the technical means and effectiveness of this application's objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of a contour bend detection method, system, and device for aluminum bar quality inspection proposed in this application. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0045] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0046] This application provides a contour bend detection method for aluminum bar quality inspection. This method incorporates a bend detection process before the straightening process to detect truly bent aluminum bars. Based on the characteristics of the physical changes in bent aluminum bars, the method analyzes the movement of the aluminum bars during conveyor belt transportation to screen out bent aluminum bars. Only truly bent aluminum bars are straightened.

[0047] The following is a detailed description of a specific method for detecting the contour bending of aluminum bars provided by the present application in conjunction with the accompanying drawings. Figure 1 As shown, the method includes:

[0048] S11. In response to receiving a demolding completion signal sent by the demolding component, obtaining a first image of each aluminum bar; in response to receiving a transmission signal, obtaining multiple frames of second images of each aluminum bar.

[0049] Among them, the transmission signal indicates that the aluminum rod is in the process of being transferred from the demolding assembly to the straightening assembly; the demolding completion signal indicates that the aluminum rod has completed demolding. It can be understood that the demolding assembly is used to demold the aluminum rod. After the aluminum rod is demolded, the demolding assembly immediately sends a demolding completion signal.

[0050] If the aluminum bar has uneven internal stress distribution after casting and shaping, it is prone to bending during the subsequent cooling process due to differences in deformation rates in different parts. Therefore, a first image of each aluminum bar can be obtained after the aluminum bar is demolded. Multiple frames of second images of each aluminum bar are obtained during the process of transferring the aluminum bar from the demolding assembly to the straightening assembly. When the aluminum bar is transferred to the starting end of the conveyor belt, the first frame of the second image is captured. Thereafter, each time the conveyor belt transfers the aluminum bar a preset distance, the high-frame camera captures a second frame of the image. The preset distance can be set according to actual conditions, for example, 0.5, 0.55, etc. Multiple frames of the second image are acquired and sorted in chronological order to obtain a second image sequence corresponding to each aluminum bar.

[0051] like Figure 2As shown, the aluminum rod is demoulded after the casting process is completed. After demoulding, it is transferred to the straightening assembly via a conveyor belt for the straightening process. Two high-frame cameras can be set directly above the conveyor belt. The first high-frame camera is set vertically directly above the starting end of the conveyor belt to capture the first image immediately after the aluminum rod completes the casting process and is demoulded. The second high-frame camera can be set vertically directly above the midpoint of the conveyor belt, or directly above other positions of the conveyor belt to ensure that the complete outline image of the aluminum rod can be obtained. It is used to obtain multiple frames of second images of each aluminum rod during the process of transferring the aluminum rod from the demoulding assembly to the straightening assembly of the straightening process. The perspectives of the multiple frames of the second image can be aligned and corrected by affine transformation. Both high-frame cameras use a high frame rate setting that dynamically matches the transmission speed of the conveyor belt to ensure that the image in motion is free of ghosting. The frame rate calculation formula is as follows:

[0052] ;

[0053] in, represents the frame rate of the high-frame camera, v represents the conveyor speed, and d represents the maximum displacement deviation allowed in a single frame image. That is, within the time interval between two adjacent frames captured by the camera, the distance the aluminum bar moves along the conveyor direction cannot exceed d. Otherwise, the image will be blurred due to motion, leading to detection errors. The maximum displacement deviation can be set according to actual conditions, such as 0.5, 0.55, etc.

[0054] It can also be equipped with a uniform backlight system, combined with polarizing optical components to eliminate reflective interference on the aluminum bar surface, making the aluminum bar's outline and edges clearly discernible. Two high-frame cameras are mounted on a vibration-absorbing base to avoid the impact of production line vibration on shooting accuracy. The parameters of the two high-frame cameras are consistent to ensure that the images in the first and second image sequences are comparable.

[0055] S12. Determine the primary screening aluminum bars from the plurality of aluminum bars according to the contour difference index of the aluminum bars.

[0056] The contour difference index is obtained based on analyzing the offset between each edge contour point of the first image of the aluminum bar and the second image of the first frame.

[0057] From a plurality of aluminum bars, aluminum bars having a profile difference index greater than an index threshold may be determined as primary screening aluminum bars, wherein the index threshold is set according to actual conditions, for example, 0.8, 0.85, etc.

[0058] If an aluminum bar exhibits uneven internal stress distribution after casting, it is susceptible to bending during the subsequent cooling process due to differential deformation rates across different parts. To accurately identify potential bending risks, a first image is captured immediately after the bar is demolded to record its original contour. The second image is captured just as the bar is being transported onto the conveyor. The time window between these two captures covers the critical stage of cooling from high temperature. During this process, subtle deformations may accumulate due to natural cooling, while potential bending trends may be accelerated by transport vibrations. By comparing the changes in contour features between the two images, bars with abnormal surface morphology can be identified. Therefore, a contour difference index can be derived by analyzing the offset between each edge contour point in the first and second images.

[0059] In one embodiment, the profile difference index is obtained according to the following steps:

[0060] Extracting multiple edge contour points of the first image and the first frame second image based on the Canny operator;

[0061] determining, based on coordinate differences between a plurality of edge contour points of the first image and a plurality of edge contour points of the first frame second image, a radial offset between each edge contour point of the first image and the first frame second image, and determining an edge contour point having a radial offset greater than a preset offset threshold as an abnormal contour point;

[0062] The profile difference index is determined based on the length of the abnormal curve formed by connecting all abnormal profile points, the length of the aluminum rod, and the sum of the radial offsets of all abnormal profile points.

[0063] The offset threshold is set according to the actual situation, for example, it can be 0.3, 0.35, etc.

[0064] The edge detection algorithm such as Canny operator can be used to extract multiple edge contour points of the aluminum bar in the first image and the second image of the first frame, and then the effective edge contour points are screened by double thresholds. , then the edge contour point is determined as a strong edge point. When the edge contour point satisfies , and the point is connected to a strong edge point, then the edge contour point is determined as a weak edge point. Edge contour points The gradient, is the high threshold, The value can be set according to the actual situation, for example, it can be set to 80~100. is the low threshold, Can be set to .

[0065] By identifying strong edge points on the edge of the aluminum bar, such as the clear boundary between the main body of the aluminum bar and the background, as the key contour of the aluminum bar edge, it is possible to ensure that the main contour of the aluminum bar is not lost. At the same time, only weak edges connected to the strong edge are retained, and isolated noise points are filtered out to obtain the complete edge contour of the aluminum bar. Then, the edge contours of the aluminum bar in the first image and the second image of the first frame are aligned through the image registration algorithm to ensure the unity of the coordinate system.

[0066] The radial offset between each edge contour point can be calculated based on the coordinate difference between the corresponding edge contour points in the first image and the second image of the first frame. ,in, The radial offset can be obtained by aligning the edge contours of the aluminum rod in the first image and the second image of the first frame through the image registration algorithm to obtain the coordinates of the ath edge contour point in the first image and the second image of the first frame. and The edge contour points with radial offsets greater than the offset threshold are determined as abnormal contour points. The contour difference index is determined based on the length of the abnormal curve formed by connecting all abnormal contour points, the length of the aluminum rod, and the sum of the radial offsets of all abnormal contour points.

[0067] In one embodiment, the profile difference index is determined based on the length of the abnormal curve formed by connecting all abnormal profile points, the length of the aluminum bar, and the sum of the radial offsets of all abnormal profile points, including:

[0068] The contour difference index is determined based on the product of the line segment ratio and the anomaly ratio; the line segment ratio indicates the ratio of the length of the abnormal curve to the length of the aluminum rod, the anomaly ratio indicates the ratio of the sum of the radial offsets of all abnormal contour points to the number of offsets, and the offset number indicates the product of the total number of abnormal contour points and the offset threshold.

[0069] The offset threshold is set according to the actual situation, for example, it can be 0.3, 0.35, etc.

[0070] When an aluminum bar bends, its contour changes often show a large, continuous deformation along the axial direction, which is the length of the aluminum bar itself. This means that a certain edge will extend from a local area to the entire bar, resulting in a large-scale deviation. Local contour changes are often caused by interfering factors such as surface stains and oxide film shedding, and are usually small, discontinuous anomalies. Therefore, the length of the abnormal curve formed by connecting all abnormal contour points can be determined first. and aluminum rod length , according to the length of the abnormal curve and aluminum rod length Calculate the line segment ratio by the ratio of , and then determine the sum of the radial offsets of all abnormal contour points Then calculate the ratio of the sum of the radial offsets of all abnormal contour points to the number of offsets to get the abnormal ratio. The product of is used to calculate the amount of deviation, and finally the contour difference index is calculated to quantify the integrity of the abnormal area:

[0071] ;

[0072] Among them, CDI is the contour difference index, is the length of all abnormal curves connected by all abnormal contour points. If the adjacent abnormal contour points are continuous in the axial direction, for example, the interval is ≤10, they can be merged into an abnormal curve. The length of all abnormal curves is accumulated to get . is the length of the aluminum rod, is the sum of the radial offsets of all abnormal contour points, n is the total number of abnormal contour points, b is the bth abnormal contour point, is the offset threshold, is the radial offset of the bth abnormal contour point. is the line segment ratio, which can be used to represent the proportion of continuous abnormal curves. If the aluminum rod is bent, the abnormal contour points will be continuously distributed along the axial direction. If it is disturbed by stains, oxide films, etc., it will only affect the local area. Usually small, relatively Offset strength Corresponding to the overall bending degree of the aluminum bar, if the aluminum bar is bent, the offset of the edge contour points on the same side is generally large and close; if it is disturbed by stains, oxide film, etc., only a few edge contour points will have a large offset, while most edge contour points will have a small offset. Therefore, the sum of the radial offsets of all abnormal contour points can be used to calculate the offset of the edge contour points, assuming that the offsets of all abnormal points are the threshold value. The offset strength is expressed by the ratio of the number of offsets when . When the ratio is greater than 1, it means that the offsets of abnormal contour points generally exceed the offset threshold, which means that the consistency is high.

[0073] If the CDI is greater than the threshold, the aluminum bar can be identified as a pre-screened aluminum bar. This indicates that the abnormal curve formed by the offset of the edge contour points on the same side is continuous and has a large amplitude, indicating that the aluminum bar is suspected of being bent. The threshold can be set based on actual conditions, for example, 0.8 or 0.85.

[0074] The contour difference index is calculated by calculating the continuity ratio and offset strength of the abnormal curve. This quantitative distinction between global continuity and local discreteness not only avoids the false detection of local interference as bending by traditional single-threshold detection, but also captures tiny overall bending changes, providing a robust quantitative tool for quality inspection of aluminum rod production.

[0075] S13. For a single pre-screened aluminum bar, determine the displacement mutation index and displacement change rate of each feature point in each frame based on the position difference of each feature point in the second image of adjacent frames in the second image sequence corresponding to the pre-screened aluminum bar.

[0076] Among them, the displacement mutation index indicates whether the position of each feature point has a mutation. The mutation indicates that the position of the feature points of adjacent frames has an instantaneous jump or discontinuous change. It can be understood that whether the position of each feature point has a mutation can be determined by judging whether the vibration displacement difference of the feature points of adjacent frames exceeds the threshold. The threshold is set according to the actual situation. For example, it can be 3 times the standard deviation of the vibration displacement difference of all feature points in all frames. The vibration displacement of the i-th feature point in the t-th frame can be obtained by the coordinate of the i-th feature point in the t-th frame. The average value of the coordinates of this point in all frames The vibration displacement difference is obtained by calculating the absolute value of the vibration displacement difference between the i-th feature point in the t-th frame and the t-1-th frame.

[0077] The displacement change rate indicates the magnitude of the position change of each feature point.

[0078] Each feature point is obtained through a corner detection algorithm. For example, a FAST corner detection algorithm (Features from Accelerated Segment Test) or a Harris Corner Detector algorithm can be used to extract multiple feature points on the surface of the initially screened aluminum bar. The number of feature points can be set according to actual conditions, for example, 100 or 105.

[0079] Each feature point in adjacent frames corresponds to each other. We can first extract multiple feature points on the aluminum rod, and then use the KLT optical flow algorithm (Kanade-Lucas-Tomasi Feature Tracker) to track the position of each feature point in each frame image. During the tracking process, the coordinates of the i-th feature point in the t-th frame can be recorded as , then the feature points in each frame image correspond one to one.

[0080] During the production and transportation of aluminum bars, extensive oxide film accumulation can create the illusion of bending. However, true bending is a change in the bar's overall physical form, fundamentally different from superficial changes caused by oxide film shedding. True bent bars require straightening, while bars with apparent bending due to oxide film shedding do not require straightening. Therefore, a secondary identification process is required before the bars enter the straightening assembly. As the bars travel along the conveyor belt, truly bent bars experience periodic jerking due to structural deformation. While surface protrusions caused by the oxide film may exhibit displacement accompanied by vibration, the film's brittle texture makes it susceptible to shedding during transport vibrations, resulting in irregular, sudden changes in the jerking amplitude. A second image sequence corresponding to each pre-screened bar can be used to analyze the behavior of the pre-screened bars during transportation, capturing the regular jerking caused by true bending and the abnormal vibration fluctuations caused by oxide film shedding, effectively distinguishing between bars with apparent bending and those with actual bending.

[0081] Since real bending and oxide film shedding have different effects on the surface points of the aluminum rod, real physical bending causes the vibration trajectory of the aluminum rod surface points to show periodic patterns, while oxide film shedding causes mutations in the vibration trajectory of local points. Therefore, the vibration information of the aluminum rod surface points can be obtained by extracting the characteristic points on the aluminum rod surface and tracking their position changes in the time-series image, that is, the second image sequence.

[0082] The FAST corner detection algorithm can be used to uniformly extract 100 feature points on the surface of the aluminum bar. In order to avoid the error interference of offsetting the real boundary by several pixels during the contour detection process, the edge contour points less than 5 pixels away from the aluminum bar contour can be filtered. The KLT optical flow algorithm is used to track the position of each feature point in each frame image. The coordinate system is established with the geometric center point of the aluminum bar as the origin. The coordinates of the i-th feature point in the t-th frame during the tracking process can be recorded as , x is the horizontal coordinate, Indicates the horizontal position of the i-th point in the t-th frame, y is the vertical coordinate, represents the vertical position of the i-th point at the t-th frame, and each feature point in each frame image corresponds one to one.

[0083] The translational jitter of the conveyor belt appears in the image as a displacement of the aluminum bar as a whole in a certain direction. By aligning the geometric center point of the aluminum bar to the origin, this global translation can be converted into a coordinate system transformation, so that subsequent analysis only focuses on the deformation of the aluminum bar itself rather than the overall movement.

[0084] Align the center of the aluminum rod in each frame image to the geometric center of the aluminum rod in the first frame image. Assume that the coordinates of the geometric center point of the aluminum rod in the first frame and the second image are , then the subsequent multi-frame second image needs to be translated to move the geometric center point of the aluminum bar in each frame to The geometric center point of the second image of the first frame Align.

[0085] In one embodiment, based on the position difference of each feature point in the second image of adjacent frames in the second image sequence corresponding to the primary screening aluminum bar, the displacement mutation index and displacement change rate of each feature point in each frame are determined, including:

[0086] Based on the absolute difference between the first vibration displacement and the second vibration displacement and the first vibration displacement, determining the displacement change rate of each feature point in each frame; the first vibration displacement indicates the vibration displacement of each feature point in the second image of the first target frame, the first vibration displacement is calculated based on the Euclidean distance between the coordinates of each feature point in the first target frame and the average value of its coordinates in all frames, and the first target frame indicates a frame that is closer to the front among adjacent frames; the second vibration displacement indicates the vibration displacement of each feature point in the second image of the second target frame, the second vibration displacement is calculated based on the Euclidean distance between the coordinates of each feature point in the second target frame and the average value of its coordinates in all frames, and the second target frame indicates a frame that is closer to the back among adjacent frames;

[0087] Based on the absolute difference between the first vibration displacement and the second vibration displacement, a displacement mutation index of each feature point in each frame is determined.

[0088] The bending of a real aluminum bar causes deformation of its overall structure. The vibration of each characteristic point on the bar's surface exhibits periodic and continuous changes during transportation, with smooth displacement changes between adjacent frames without sudden changes. However, the oxide film is fragile and easily detaches during transportation, causing the vibration trajectory of each characteristic point on the corresponding surface to undergo irregular sudden changes, with the displacement change rate between adjacent frames suddenly increasing. Therefore, by quantifying the continuity and sudden change frequency of the vibration trajectory of each characteristic point on the aluminum bar's surface, it is possible to distinguish between true bending and oxide film interference.

[0089] The first target frame indicates a front frame among adjacent frames, and the second target frame indicates a back frame among adjacent frames. It can be understood that when the first target frame is the t-th frame, the second target frame is the t+1-th frame; when the first target frame is the t-1-th frame, the second target frame is the t-th frame.

[0090] The first vibration displacement indicates the vibration displacement of each feature point in the second image of the first target frame. When the first target frame is the t-1 frame, the first vibration displacement Indicates the vibration displacement of the i-th feature point in the t-1 frame, by calculating the coordinates of the i-th feature point in the t-1 frame The average value of the coordinates of this point in all frames The Euclidean distance between them is obtained, the i-th feature point can be any feature point on the aluminum rod, and the t-1-th frame can be any frame in the second image sequence, thereby calculating the vibration displacement of each feature point in each frame.

[0091] The second vibration displacement indicates the vibration displacement of each feature point in the second image of the second target frame. When the second target frame is the t-th frame, the second vibration displacement Indicates the vibration displacement of the i-th feature point in the t-th frame, by calculating the coordinates of the i-th feature point in the t-th frame The average value of the coordinates of this point in all frames The Euclidean distance between them is obtained, the i-th feature point can be any feature point on the aluminum rod, and the t-th frame can be the second frame in the second image sequence and any frame thereafter, thereby calculating the vibration displacement of each feature point in each frame.

[0092] First vibration displacement and the second vibration displacement The absolute difference can be expressed as The displacement change rate of each feature point in each frame can be determined based on the absolute difference between the first vibration displacement and the second vibration displacement and the first vibration displacement, and the displacement mutation index of each feature point in each frame can be determined based on the absolute difference between the first vibration displacement and the second vibration displacement.

[0093] In one embodiment, determining the displacement change rate of each feature point in each frame based on the absolute difference between the first vibration displacement and the second vibration displacement and the first vibration displacement includes:

[0094] For a single feature point, determine the displacement change rate of the feature point in each frame based on the ratio of the absolute difference between the first vibration displacement of the feature point and the second vibration displacement of the feature point to the first vibration displacement of the feature point;

[0095] The ratio of the absolute difference between the first vibration displacement and the second vibration displacement of each feature point in each frame to the first vibration displacement is calculated to determine the displacement change rate of each feature point in each frame.

[0096] Each frame of the second image has multiple feature points, so for the i-th feature point in each frame of the second image, the first vibration displacement of the i-th feature point in the t-1 frame can be calculated The second vibration displacement of the i-th feature point in the t-th frame The absolute difference , and then calculate With the first vibration displacement The ratio of , we get:

[0097] ;

[0098] in, It represents the displacement change rate of the i-th feature point in the t-th frame relative to the t-1-th frame, is the first vibration displacement of the i-th feature point in the t-1 frame, by calculating the coordinates of the i-th feature point in the t-1 frame The average value of the coordinates of this point in all frames The Euclidean distance between them is obtained. is the second vibration displacement of the i-th feature point in the t-frame, by calculating the coordinates of the i-th feature point in the t-frame The average value of the coordinates of this point in all frames The Euclidean distance between them can be obtained. Thus, the ratio of the absolute difference between the first vibration displacement and the second vibration displacement of each feature point in each frame to the first vibration displacement can be calculated to determine the displacement change rate of each feature point in each frame.

[0099] The absolute difference can guarantee The result is positive, the denominator The displacement changes of each characteristic point can be normalized to eliminate the influence of initial displacement differences between different characteristic points. When the aluminum bar is truly bent, the displacement change rate of each characteristic point is small and continuous. However, when the oxide film on the aluminum bar falls off, the displacement change rate of the corresponding characteristic point will increase significantly due to the sudden change in the vibration trajectory.

[0100] In one embodiment, determining the displacement mutation index of each feature point in each frame based on the absolute difference between the first vibration displacement and the second vibration displacement includes:

[0101] For a single feature point, if the absolute difference between the first vibration displacement and the second vibration displacement is greater than a preset mutation index, the displacement mutation index of the feature point in the second target frame is determined to be one; if not, the displacement mutation index of the feature point in the second target frame is determined to be zero;

[0102] The absolute difference between the first vibration displacement and the second vibration displacement of each feature point in each frame is calculated to obtain the displacement mutation index of each feature point in each frame.

[0103] The mutation threshold is set according to actual conditions, for example, it can be three times the standard deviation of the absolute difference of the vibration displacement of all feature points in all frames.

[0104] Each frame of the second image has multiple feature points, so for the i-th feature point in each frame of the second image, the first vibration displacement of the i-th feature point in the t-1 frame can be calculated The second vibration displacement of the i-th feature point in the t-th frame The absolute difference , determine the displacement mutation index based on the absolute difference:

[0105] ;

[0106] Among them, the displacement mutation index H Indicates the mutation value of the i-th feature point in the t-th frame, mutation index Used to distinguish normal fluctuations from abnormal mutations, represents the absolute difference in vibration displacement of the i-th feature point between the t-th frame and the t-1-th frame, that is, , if the absolute difference between the first vibration displacement of the t-1 frame and the second vibration displacement of the t frame Greater than the mutation index , it is determined that the displacement change of the feature point is significantly abnormal, that is, the possibility of the oxide film falling off is high, and the displacement mutation index H is determined. is 1 if the value is set, otherwise it is 0.

[0107] S14. Determine the surface fluctuation index of the primary screening aluminum rod based on the displacement mutation index and the displacement change rate.

[0108] In one embodiment, the surface fluctuation index of the primary screening aluminum bar is determined based on the displacement mutation index and the displacement change rate, including:

[0109] The surface fluctuation index of the primary screening aluminum bar is determined based on the displacement mutation index of each feature point in each frame in the second image sequence, the displacement change rate of each feature point in each frame in the second image sequence, the number of feature points in a single frame of the second image, and the valid frame number; the valid frame number indicates the number of second images in the second image sequence minus one.

[0110] The above steps determine the displacement mutation index and displacement change rate of each feature point in each frame. Since the KLT optical flow algorithm is used to track the position of each feature point in each frame of the second image sequence, each feature point in each second image frame has a one-to-one correspondence, meaning that the number of feature points in each frame is the same. Therefore, the number of feature points in a single second image frame can be obtained to determine the total number of feature points extracted from the aluminum bar. The effective frame number indicates the number of second images in the second image sequence minus one. If the number of second images in the second image sequence is T, the effective frame number is T-1.

[0111] In one embodiment, the surface fluctuation index of the primary screening aluminum bar is determined based on the displacement mutation index of each feature point in each frame of the second image sequence, the displacement change rate of each feature point in each frame of the second image sequence, the number of feature points in a single frame of the second image, and the number of valid frames, including:

[0112] The surface fluctuation index of the primary screening aluminum bar is determined based on the ratio of the sum of the displacements to the sum of the characteristic points; the sum of the displacements indicates the sum of the products of the displacement mutation index of each characteristic point in each frame in the second image sequence and the displacement change rate of each characteristic point in each frame in the second image sequence, and the sum of the characteristic points indicates the product of the number of characteristic points in a single frame of the second image and the number of valid frames.

[0113] First, calculate the sum of the product of the displacement mutation index of each feature point in each frame of the second image and the displacement change rate of each feature point in each frame of the second image sequence to obtain the sum of the displacements. , where N is the number of feature points in a single-frame second image, that is, the number of all feature points extracted from the aluminum bar, i is the i-th feature point, T is the number of second images in the second image sequence, then T-1 is the number of valid frames, that is, the number of valid frames, and t is the t-th frame. Indicates the displacement change rate of the i-th feature point in the t-th frame, It means to accumulate all feature points (i from 1 to N) and all valid frames (t from 2 to T). Then calculate the product of the number of feature points in the second image of a single frame and the number of valid frames to get the sum of feature points. Then, the surface fluctuation index of the primary screening aluminum bar is determined based on the ratio of the sum of the displacements to the sum of the characteristic points. :

[0114] ;

[0115] It can be understood that the above-mentioned numerator only calculates the contribution of the displacement change rate of the feature point with a displacement mutation index of 1, that is, only calculates the contribution of the displacement change rate of the feature point where the mutation occurs, to avoid the interference of normal fluctuations. By accumulating the displacement change rates of all feature points that have mutated, the abnormal vibration of the surface of the aluminum rod, that is, the intensity of the mutation, is reflected. Then, by normalizing the accumulated results of the numerator, it is ensured that the surface fluctuation index is not affected by the number of feature points and the number of frames of the second image sequence.

[0116] S15. Perform bending analysis on the primary screening aluminum rod based on the surface fluctuation index to obtain analysis results.

[0117] According to the surface fluctuation index To judge the state of the primary screening aluminum bar, you can set the fluctuation threshold to judge the primary screening aluminum bar. The fluctuation threshold can be set according to the actual situation. For example, it can be set to 0.3, 0.35, etc. < fluctuation threshold, the aluminum bar screened initially is determined to be truly bent, because the vibration of true bending is continuous, with very few mutation events, and the surface fluctuation index If the surface fluctuation index If the value is greater than or equal to the fluctuation threshold, it is determined to be oxide film interference. The shedding of the oxide film will cause a sudden change in the motion state of the aluminum rod, a high displacement change rate, and a high surface fluctuation index SDFI.

[0118] This application can automatically screen out the surface fluctuation index by performing a secondary discrimination on the aluminum bar before it enters the straightening assembly. The actual bent aluminum bars below the threshold are transferred to the straightening assembly for targeted treatment; For aluminum bars above the threshold, the system will determine that their condition is normal or only affected by the oxide film, and directly skip the straightening process without entering the straightening assembly for straightening. This avoids ineffective straightening operations on non-bent aluminum bars and improves the operating efficiency of the production line.

[0119] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0120] This application also provides a contour bending detection system for aluminum bar quality inspection, such as Figure 3 As shown, the system includes:

[0121] an acquisition module 31 configured to acquire a first image of each aluminum bar in response to receiving a demolding completion signal from the demolding assembly; and acquire multiple frames of second images of each aluminum bar in response to receiving a transmission signal, wherein the transmission signal indicates that the aluminum bar is in the process of being transferred from the demolding assembly to the straightening assembly;

[0122] A first determination module 32 is configured to determine the preliminarily screened aluminum bars from the plurality of aluminum bars based on a contour difference index of the aluminum bars; the contour difference index is obtained by analyzing the offset between each edge contour point of the first image of the aluminum bar and the second image of the first frame;

[0123] The second determination module 33 is configured to determine, for a single pre-screened aluminum bar, a displacement mutation index and a displacement change rate of each feature point in each frame based on the positional differences of each feature point in adjacent frames of the second image sequence corresponding to the pre-screened aluminum bar; the displacement mutation index indicates whether the position of each feature point has undergone a mutation, and the displacement change rate indicates the magnitude of the positional change of each feature point; the feature points of adjacent frames correspond one to one, and each feature point is obtained using a corner detection algorithm;

[0124] A third determining module 34 is configured to determine a surface fluctuation index of the primary screening aluminum bar based on the displacement mutation index and the displacement change rate;

[0125] The analysis module 35 is used to perform bending analysis on the primary screening aluminum bars based on the surface fluctuation index to obtain analysis results.

[0126] For the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can be referred to the partial description of the method embodiment. The system embodiment described above is only illustrative, in which the units described as separate components may or may not be physically separated, and the components of the units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present application solution.

[0127] Figure 4 This is a schematic structural diagram of an electronic device for detecting contour bending for quality inspection of aluminum bars, shown as an example embodiment of the present application. The electronic device includes a memory, a processor, and a computer program stored in the memory and for running on the processor. When the processor executes the computer program, the method described in any of the above embodiments is implemented. Figure 4 The electronic device 40 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0128] like Figure 4 As shown, the electronic device 40 may be a general-purpose computing device, such as a server device. Components of the electronic device 40 may include, but are not limited to, the at least one processor 41, the at least one memory 42, and a bus 43 connecting various system components (including the memory 42 and the processor 41).

[0129] The bus 43 includes a data bus, an address bus, and a control bus.

[0130] The memory 42 may include a volatile memory, such as a random access memory (RAM) 421 and / or a cache memory 422 , and may further include a read-only memory (ROM) 423 .

[0131] The memory 42 may also include a program tool 425 (or utility) having a set (at least one) of program modules 424, such program modules 424 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0132] The processor 41 executes various functional applications and data processing by running the computer programs stored in the memory 42, such as the method provided in any of the above embodiments.

[0133] The electronic device 40 can also communicate with one or more external devices 44 (e.g., a keyboard, pointing device, etc.). This communication can occur via an input / output (I / O) interface 45. Furthermore, the electronic device 40 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 46. As shown, the network adapter 46 communicates with other modules of the electronic device 40 via a bus 43. It should be understood that, although not shown, other hardware and / or software modules can be used in conjunction with the electronic device 40, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, RAID (RAID) systems, tape drives, and data backup storage systems.

[0134] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, depending on the embodiment of the present application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0135] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the method provided in any of the above embodiments when the program is executed by a processor.

[0136] The readable storage medium may include, but is not limited to, a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0137] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0138] An embodiment of the present application further provides a computer program product, including a computer program, which implements any of the above methods when executed by a processor.

[0139] The program code for executing the computer program product of the present application may be written in any combination of one or more programming languages, and the program code may be executed entirely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or entirely on the remote device.

[0140] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0141] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the spirit of the present application, and such modifications and improvements are all within the scope of protection of the present application.

[0142] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A contour bending detection method for aluminum bar quality inspection, characterized in that: The method comprises: In response to receiving a demolding completion signal from the demolding assembly, a first image of each aluminum bar is acquired; in response to receiving a transmission signal, multiple frames of second images of each aluminum bar are acquired; the transmission signal indicates that the aluminum bar is in the process of being transferred from the demolding assembly to the straightening assembly; Determining the preliminarily screened aluminum bars from the plurality of aluminum bars according to an aluminum bar contour difference index obtained by analyzing the offset between each edge contour point of the first image and the second image of the first frame; For a single pre-screened aluminum bar, the displacement mutation index and displacement change rate of each feature point in each frame are determined based on the positional differences of each feature point in the second images of adjacent frames in the second image sequence corresponding to the pre-screened aluminum bar. The displacement mutation index indicates whether the position of each feature point has changed suddenly, and the displacement change rate indicates the magnitude of the position change of each feature point. The feature points of adjacent frames correspond one to one, and each feature point is obtained using a corner point detection algorithm. Determining a surface fluctuation index of the primary screening aluminum rod based on the displacement mutation index and the displacement change rate; Performing a bending analysis on the primary screening aluminum rod based on the surface fluctuation index to obtain an analysis result; The profile difference index is obtained according to the following steps: Extracting multiple edge contour points of the first image and the first frame second image based on the Canny operator; determining, based on coordinate differences between a plurality of edge contour points of the first image and a plurality of edge contour points of the first frame second image, a radial offset between each edge contour point of the first image and the first frame second image, and determining an edge contour point having a radial offset greater than a preset offset threshold as an abnormal contour point; The profile difference index is determined based on the length of the abnormal curve formed by connecting all abnormal profile points, the length of the aluminum rod, and the sum of the radial offsets of all abnormal profile points.

2. The contour bending detection method for aluminum bar quality inspection according to claim 1, characterized in that: The contour difference index is determined based on the length of the abnormal curve formed by connecting all abnormal contour points, the length of the aluminum rod, and the sum of the radial offsets of all abnormal contour points, including: The contour difference index is determined based on the product of the line segment ratio and the anomaly ratio; the line segment ratio indicates the ratio of the length of the abnormal curve to the length of the aluminum rod, the anomaly ratio indicates the ratio of the sum of the radial offsets of all abnormal contour points to the number of offsets, and the offset number indicates the product of the total number of abnormal contour points and the offset threshold.

3. The contour bending detection method for aluminum bar quality inspection according to claim 1, characterized in that: The method of determining the displacement mutation index and displacement change rate of each feature point in each frame based on the position difference of each feature point in the second image of adjacent frames in the second image sequence corresponding to the primary screened aluminum bar includes: Based on the absolute difference between the first vibration displacement and the second vibration displacement and the first vibration displacement, determining the displacement change rate of each feature point in each frame; the first vibration displacement indicates the vibration displacement of each feature point in the second image of the first target frame, the first vibration displacement is calculated based on the Euclidean distance between the coordinates of each feature point in the first target frame and the average value of its coordinates in all frames, and the first target frame indicates a frame that is closer to the front among adjacent frames; the second vibration displacement indicates the vibration displacement of each feature point in the second image of the second target frame, the second vibration displacement is calculated based on the Euclidean distance between the coordinates of each feature point in the second target frame and the average value of its coordinates in all frames, and the second target frame indicates a frame that is closer to the back among adjacent frames; Based on the absolute difference between the first vibration displacement and the second vibration displacement, a displacement mutation index of each feature point in each frame is determined.

4. The contour bending detection method for aluminum bar quality inspection according to claim 3, characterized in that: The determining the displacement change rate of each feature point in each frame based on the absolute difference between the first vibration displacement and the second vibration displacement and the first vibration displacement includes: For a single feature point, determine the displacement change rate of the feature point in each frame based on the ratio of the absolute difference between the first vibration displacement of the feature point and the second vibration displacement of the feature point to the first vibration displacement of the feature point; The ratio of the absolute difference between the first vibration displacement and the second vibration displacement of each feature point in each frame to the first vibration displacement is calculated to determine the displacement change rate of each feature point in each frame.

5. The contour bending detection method for aluminum bar quality inspection according to claim 3, characterized in that: Determining the displacement mutation index of each feature point in each frame based on the absolute difference between the first vibration displacement and the second vibration displacement includes: For a single feature point, if the absolute difference between the first vibration displacement and the second vibration displacement is greater than a preset mutation index, the displacement mutation index of the feature point in the second target frame is determined to be one; if not, the displacement mutation index of the feature point in the second target frame is determined to be zero; The absolute difference between the first vibration displacement and the second vibration displacement of each feature point in each frame is calculated to obtain the displacement mutation index of each feature point in each frame.

6. The contour bending detection method for aluminum bar quality inspection according to claim 1, characterized in that: The determining of the surface fluctuation index of the primary screening aluminum bar based on the displacement mutation index and the displacement change rate includes: The surface fluctuation index of the initially screened aluminum bar is determined based on the displacement mutation index of each feature point in each frame in the second image sequence, the displacement change rate of each feature point in each frame in the second image sequence, the number of feature points in a single frame of the second image, and the valid frame number; the valid frame number indicates the number of second images in the second image sequence minus one.

7. The contour bending detection method for aluminum bar quality inspection according to claim 6, characterized in that: The method of determining the surface fluctuation index of the pre-screened aluminum bar based on the displacement mutation index of each feature point in each frame of the second image sequence, the displacement change rate of each feature point in each frame of the second image sequence, the number of feature points in a single frame of the second image, and the number of valid frames includes: The surface fluctuation index of the initially screened aluminum rod is determined based on the ratio of the sum of the displacements to the sum of the characteristic points; the sum of the displacements indicates the sum of the products of the displacement mutation index of each characteristic point in each frame of the second image sequence and the displacement change rate of each characteristic point in each frame of the second image sequence, and the sum of the characteristic points indicates the product of the number of characteristic points in a single frame of the second image and the number of valid frames.

8. A contour bending detection system for aluminum bar quality inspection, characterized in that: The system comprises: an acquisition module, configured to acquire a first image of each aluminum bar in response to receiving a demolding completion signal from the demolding assembly; and acquire multiple frames of second images of each aluminum bar in response to receiving a transmission signal, wherein the transmission signal indicates that the aluminum bar is in the process of being transferred from the demolding assembly to the straightening assembly; A first determination module is configured to determine a preliminarily screened aluminum bar from a plurality of aluminum bars based on a contour difference index of the aluminum bars, wherein the contour difference index is obtained by analyzing an offset between each edge contour point of the first image of the aluminum bar and the second image of the first frame; The second determination module is configured to determine, for a single pre-screened aluminum bar, a displacement mutation index and a displacement change rate of each feature point in each frame based on the positional differences of each feature point in adjacent frames of a second image sequence corresponding to the pre-screened aluminum bar; the displacement mutation index indicates whether the position of each feature point has a mutation, and the displacement change rate indicates the magnitude of the position change of each feature point; the feature points of adjacent frames correspond one to one, and each feature point is obtained using a corner detection algorithm; a third determining module, configured to determine a surface fluctuation index of the primary screening aluminum rod based on the displacement mutation index and the displacement change rate; An analysis module is used to perform bending analysis on the primary screening aluminum bars based on the surface fluctuation index to obtain analysis results; The profile difference index is obtained according to the following steps: Extracting multiple edge contour points of the first image and the first frame second image based on the Canny operator; determining, based on coordinate differences between a plurality of edge contour points of the first image and a plurality of edge contour points of the first frame second image, a radial offset between each edge contour point of the first image and the first frame second image, and determining an edge contour point having a radial offset greater than a preset offset threshold as an abnormal contour point; The profile difference index is determined based on the length of the abnormal curve formed by connecting all abnormal profile points, the length of the aluminum rod, and the sum of the radial offsets of all abnormal profile points.

9. An electronic device for detecting contour bending for quality inspection of aluminum bars, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Images