Method and system for detecting installation quality of middle part of belt conveyor

Abstract

The invention belongs to the technical field of image data processing, and particularly relates to a belt conveyor middle part installation quality detection method and system, and the method comprises the steps: obtaining an initial direction vector of each pixel point of an image of a belt conveyor middle part through frequency domain analysis; for each pixel point, obtaining an anisotropic kernel function based on direction similarity and carrying out iterative updating on the initial direction vector to obtain a final direction vector; acquiring an axis positioning score based on divergence of a normal vector, and forming an axis positioning map; and extracting a main central axis skeleton point set of the axis positioning map, fitting a straight line, comparing an error from the skeleton point to the fitted straight line with a preset tolerance, and judging whether the installation quality is qualified or not. According to the method, the problems of linear feature fracture and unreliable direction field caused by gaps in industrial images are solved, and robust and high-precision automatic detection of the straightness of the belt conveyor is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image data processing. More particularly, the present application relates to a method and system for detecting installation quality of a middle part of a belt conveyor. BACKGROUND

[0002] The belt conveyor is an indispensable continuous material conveying equipment in the industrial fields of mines, ports and the like. The installation quality of the belt conveyor, in particular the straightness of the longitudinal beam of the middle part, is directly related to the running stability, service life and production safety of the conveyor. The traditional manual detection method is inefficient, highly subjective and has safety risks. Therefore, it has become a trend in the industry to use machine vision technology to perform automatic and high-precision installation quality detection.

[0003] In actual detection scenarios, the industrial field environment is complex, with strong noise interference such as dust, uneven lighting and glare. The longitudinal beam of the belt conveyor is usually composed of multiple segments spliced together, and there is a physical gap between the segments. These factors cause the linear features of the longitudinal beam in the collected images to be broken, blurred or submerged in noise, making it difficult to extract the main central axis of the longitudinal beam.

[0004] In the prior art, a local direction estimation method based on frequency domain analysis is often used to obtain the direction of linear structures in an image. This method performs Fourier transform on each local region of the image, analyzes the frequency spectrum characteristics to determine the dominant texture direction. However, this method only relies on local information. When processing the physical connection gap of the longitudinal beam or the background area without obvious texture, the calculated direction is unreliable or even random due to the lack of effective structure information in the local neighborhood window, resulting in a broken direction field at the key gap position, which cannot form a global direction field that penetrates the entire longitudinal beam. It is difficult to accurately fit the complete central axis and evaluate its straightness, and the robustness and precision of the detection are severely restricted. SUMMARY

[0005] To solve the technical problem that the prior art only relies on local information and cannot accurately fit the complete central axis, the present application provides solutions in the following aspects.

[0006] In a first aspect, the present application provides a method for detecting installation quality of a middle part of a belt conveyor, comprising: acquiring a gray-scale image of the middle part of the belt conveyor; recording any pixel point of the gray-scale image as a target pixel point; applying a window function to a neighborhood window of the target pixel point and obtaining an initial direction vector of the target pixel point based on Fourier transform; obtaining an anisotropic kernel function between the target pixel point and the neighborhood window pixel points of the target pixel point based on the distance between the target pixel point and the neighborhood window pixel points and the similarity of the initial direction vectors of the target pixel point and the neighborhood window pixel points, iteratively updating the initial direction vector of the target pixel point with the anisotropic kernel function to obtain a final direction vector of the target pixel point; obtaining a normal vector of the target pixel point according to the final direction vector of the target pixel point; obtaining an axis positioning score of the target pixel point based on the divergence of the normal vector of the target pixel point, and grouping the axis positioning scores of all pixel points into an axis positioning map; extracting a main central axis skeleton point set of the axis positioning map and fitting it into a straight line with a least square method, and calculating the error of the skeleton points to the fitted straight line; comparing the error with a preset tolerance to determine whether the installation quality of the middle part of the belt conveyor is qualified.

[0007] The present application adopts a technical path of obtaining an initial direction from frequency domain analysis and iteratively optimizing through anisotropic smoothing, can accurately spread and fill the gap area of the feature interruption with the direction information of the conveyor entity part, and extract a continuous main central axis covering the full length of the longitudinal beam, thereby providing reliable technical support for realizing automatic high-precision installation quality detection.

[0008] Preferably, the application of the window function to the neighborhood window of the target pixel point comprises: applying a Hanning window function to the neighborhood window of the target pixel point.

[0009] The present application improves the calculation accuracy of the initial direction vector by applying a Hanning window function before Fourier transform, effectively suppresses the spectral leakage artifacts caused by the image neighborhood window interception, makes the frequency domain energy more accurately correspond to the real structure direction, provides high-quality input for the subsequent iterative optimization, and further enhances the robustness of the entire detection method.

[0010] Preferably, the anisotropic kernel function between the target pixel point and the neighborhood window pixel points of the target pixel point satisfies the expression: ; wherein, represents the anisotropic kernel function value between the target pixel point and the neighborhood window pixel points of the target pixel point; represents the target pixel point; represents the neighborhood window pixel point; is the iteration number; represents the pixel point In the first the direction vector at the second iteration; denotes a pixel point at the first iteration the direction vector at the second iteration; denotes a first hyper-parameter; denotes a second hyper-parameter; denotes a dot product operation of vectors; denotes a natural exponential function; denotes an absolute value symbol.

[0011] The anisotropic kernel function of the application can effectively bridge the structural breakpoints of the longitudinal beam of the conveyor in the image, and form a continuous and smooth final direction field. When the anisotropic kernel function iteratively updates the direction, it can adaptively give higher weights to the pixels in the neighborhood window that are consistent with the direction of the center point, so that the correct direction information can flow from the structural entity part to the gap area, while suppressing the interference of background noise, and finally obtain a continuous and accurate direction field at the physical gap, which lays a foundation for subsequent main centerline positioning.

[0012] Preferably, the first hyper-parameter is set to 0.8.

[0013] Preferably, the second hyper-parameter is set to 2.0.

[0014] Preferably, the normal vector of the target pixel point is obtained according to the final direction vector of the target pixel point, including: rotating the final direction vector of the target pixel point clockwise by 90° as the normal vector of the target pixel point.

[0015] Preferably, the axis positioning score of the target pixel point satisfies the expression: ; wherein, denotes the target pixel point, denotes the axis positioning score of the target pixel point . and denote a first sub-neighborhood window and a second sub-neighborhood window in a super-size neighborhood window centered on the target pixel point, the super-size neighborhood window being a neighborhood window with a side length of times the expected width of the longitudinal beam; denotes a pixel point in the sub-neighborhood window . denotes a pixel point in the sub-neighborhood window . and denote the normal vector of the pixel point and the normal vector of the pixel point , respectively. denotes divergence.

[0016] The present application can clearly highlight the main central axis of the longitudinal beam on the axis positioning map by using the divergence characteristics of the normal vector field, and the axis positioning score expression obtained can capture the center of the positive and negative symmetric divergence extreme band on both sides of the longitudinal beam. Only when the pixel point is located on the true main central axis, the score is maximized, so that the position of the main central axis is clearly indicated, and the difficulty and uncertainty of subsequent extraction are reduced.

[0017] Preferably, the method further comprises: performing binaryzation processing on the axis positioning map to obtain a binary image; applying a morphological skeleton extraction algorithm to the binary image to obtain a single-pixel-width main central axis skeleton; and performing connected component analysis on the thinned main central axis skeleton, and retaining the main central axis skeleton segment with the longest length as the skeleton point set of the main central axis.

[0018] The present application uses a morphological skeleton extraction algorithm to obtain the main central axis of the axis positioning map, effectively avoids the inaccuracy of the gradient direction caused by local gray level fluctuations or noise interference on the axis positioning map, and further prevents the breakage or deviation of the thinned main central axis; the connected component analysis retains the skeleton segment with the longest length, which can accurately separate the main central axis and remove the isolated short skeleton formed by noise points, ensuring the accuracy of the final skeleton point set, thereby providing a more reliable data basis for subsequent straightness error calculation.

[0019] Preferably, the method further comprises: calculating the error of the skeleton point to the fitted straight line; and comparing the error with a preset tolerance to determine whether the installation quality of the intermediate part of the belt conveyor is qualified, wherein the error of the skeleton point to the fitted straight line is the root mean square of the perpendicular distance of all skeleton points to the fitted straight line, and when the root mean square is less than or equal to the preset tolerance, it is determined that the installation quality is qualified, and when the root mean square is greater than the preset tolerance, it is determined that the installation quality is unqualified.

[0020] In a second aspect, the present application provides a belt conveyor intermediate part installation quality detection system, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned belt conveyor intermediate part installation quality detection method is realized.

[0021] By using the above technical solution, the above-mentioned belt conveyor intermediate part installation quality detection method is generated into a computer program and stored in the memory to be loaded and executed by the processor, so that a terminal device is made according to the memory and the processor, and the use is convenient.

[0022] The present application has the following advantages: The application utilizes reliable direction information of the conveyor entity part to intelligently propagate and fill the correct structure direction to the gap area, thereby forming a continuous and smooth direction field covering the whole length of the longitudinal beam, so that the straightness detection is no longer subject to the physical continuity of the structure, and the robustness and reliability of the evaluation result under complex working conditions are improved.

[0023] The application can highlight the position of the main central axis on the axis positioning map in the form of high brightness and high contrast by constructing a positioning score capable of maximizing the opposite divergence response of the conveyor edge, and then the high-light response band is refined into a single-pixel width accurate line through a non-maximum suppression algorithm, thereby providing an accurate geometric basis for subsequent quantitative calculation, and the accuracy of the entire detection method is improved.

[0024] The application calculates the root mean square error value by comparing the extracted main central axis skeleton point set with the ideal straight line fitted by the least square method, and uses the root mean square error value as the error of the straightness of the longitudinal beam, thereby providing a unified and repeatable judgment standard for the installation quality acceptance of the belt conveyor, and meeting the needs of industrial field automation detection. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 is a flow chart schematically showing a belt conveyor middle part installation quality detection method in the application. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the application.

[0027] The specific embodiments of the application will be described in detail below with reference to the drawings.

[0028] The embodiments of the application disclose a belt conveyor middle part installation quality detection method, referring to Figure 1 , including steps S1-S4: S1, obtaining a gray-scale image of the middle part of the belt conveyor; any pixel point of the gray-scale image is recorded as a target pixel point; and an initial direction vector of the target pixel point is obtained based on Fourier transform after applying a window function to a neighborhood window of the target pixel point.

[0029] It should be noted that this invention calculates an initial structural orientation for each pixel in the image, reflecting its local dominant texture, providing a foundation for subsequent orientation field smoothing. Due to the presence of strong noise interference such as dust and glare in industrial environments like underground coal mines, this invention employs a frequency domain analysis-based method to improve the robustness of the orientation calculation.

[0030] Specifically, grayscale images of the middle region of the belt conveyor are acquired using image acquisition equipment such as industrial cameras. ; Record pixels For the target pixel, extract an area centered on the target pixel with a size of [value missing]. neighborhood window The size of the neighborhood window should be large enough to encompass local texture features without obscuring the orientation of different structures. A window function is applied to preprocess the pixel grayscale values ​​within the neighborhood window to reduce potential spectral leakage during subsequent Fourier transforms. A two-dimensional discrete Fourier transform (2D-DFT) is performed on the windowed neighborhood window data to obtain its corresponding spectrum. Linear structures such as conveyor beams exhibit regular textures in the spatial domain, which correspond to specific energy concentration areas in the frequency domain. In the spectrum, the coordinates of the point with the strongest energy (excluding the center point) are identified and located. The direction vector of this coordinate is perpendicular to the dominant texture direction within the neighborhood window in the spatial domain. A unit vector orthogonal to this direction is calculated and defined as the target pixel. Initial direction vector at The initial direction vectors of all pixels form the initial direction field. The initial direction vectors of pixels located in the longitudinal beam region are relatively accurate and consistent, while the initial direction vectors of pixels located in the gaps between segments and the background region may appear as noise or have no clear direction.

[0031] It should be noted that the neighborhood window size in this embodiment... Select 15 pixels; select Hanning window as the window function. In other embodiments, implementers can select the neighborhood window size and window function according to actual needs.

[0032] S2. Based on the distance between the target pixel and its neighboring window pixels and the similarity of the initial direction vectors of the target pixel and its neighboring window pixels, obtain the anisotropic kernel function between the target pixel and its neighboring window pixels. Use the anisotropic kernel function to iteratively update the initial direction vector of the target pixel to obtain the final direction vector of the target pixel.

[0033] It should be noted that the initial orientation field is reliable in the longitudinal beam, but it lacks orientation information for the critical gap region. This invention utilizes known reliable orientation information and propagates the correct structural orientation to the gap region through an orientation-adaptive smoothing process, while suppressing background noise interference, to generate a final orientation field that is continuous and smooth throughout the entire longitudinal beam path, including all gaps.

[0034] Specifically, in the first In the next iteration, the target pixel The direction vector satisfies the expression:

[0035] The anisotropic kernel function between the target pixel and its neighboring window pixels satisfies the following expression:

[0036] in, Represents the target pixel. Its neighboring window pixels Anisotropic kernel function values ​​between; Indicates the target pixel; Indicated by A neighborhood window centered on the center; Represents the pixels of the neighboring window; It is the number of iterations; Represents the target pixel. In the The direction vector at the next iteration; Represents the neighborhood window pixels In the The direction vector at the next iteration; This represents the first hyperparameter used to control the weight decay of spatial distance; The second hyperparameter represents the effect used to regulate directional consistency. Represents the dot product operation of vectors; Represents the natural exponential function; Indicates the absolute value symbol; This indicates a normalization operation, which converts the composite vector within the parentheses into a unit vector.

[0037] More specifically, spatial weight term It is a standard Gaussian function that makes the spatial distance from the target pixel point... The closer the neighboring window pixels Obtain higher weights; directional consistency weighting term This measures the similarity between the direction vectors of the target pixel and the pixels in its neighboring window. When the two direction vectors are completely identical, the absolute value of the dot product is... , the weight is maximum; when the two directions are perpendicular to each other, the dot product is , the weight is .

[0038] When the smoothing calculation is performed on a target pixel point located in the gap region, the pixel points from the two side rails in the neighborhood window will obtain a higher weight because their structural direction is consistent with the main direction of the side rail, and their correct direction information will be effectively filled into the gap point. The pixel points from the background region with random direction will have a very small weight because their direction is inconsistent with the direction of the side rail, and they will hardly participate in the weighted average.

[0039] After several iterations, the initial direction vector of the target pixel point becomes the final direction vector , and the final direction vector of all pixel points of the image forms a final direction field that is continuous and smooth at the side rail and the connecting gap .

[0040] It should be noted that the first hyperparameter is used to control the weight decay of the spatial distance in the anisotropic kernel function. When the first hyperparameter increases, the pixel points farther away in space will obtain a higher weight; otherwise, they will be mainly affected by the neighboring points. In this embodiment, the first hyperparameter is set to 0.8. In other embodiments, the implementer can set the first hyperparameter according to the actual implementation situation. If the physical gap of the side rail is very wide, the first hyperparameter can be appropriately increased, for example, to 1.0, so that the pixel points in the gap region can borrow reliable direction information from the side rail farther away. If the image noise is mainly manifested as local noise points, or the side rail structure is tight, it is more appropriate to keep a smaller first hyperparameter, for example, 0.7, to focus on the smoothing of the neighboring points and prevent interference from the noise points far away.

[0041] The second hyperparameter is used to regulate the influence of direction consistency in the anisotropic kernel function. When the second hyperparameter is greater than 1, the weight of the neighborhood window points with slightly deviated direction will sharply decrease, thereby enhancing the requirement for direction consistency. The selection of a value of 2.0 in this embodiment means that the requirement for direction consistency is very strict, which is suitable for the case where the side rail structure itself is clear and the initial direction field quality is good, and can effectively suppress the interference of background noise. The implementer can set the second hyperparameter according to the actual implementation situation. If the image noise interference is extremely strong, resulting in a large deviation in the initial direction field itself, the second hyperparameter may be too high, which may cause excessive suppression and result in difficulty in information propagation. At this time, the second hyperparameter can be appropriately adjusted, for example, set between 1.0 and 1.5, to increase the fault tolerance of the iterative update.

[0042] It should be further explained that the purpose of iteration is to allow reliable directional information from the longitudinal beams to intelligently propagate and fill the gap regions where features are interrupted. The choice of the number of iterations is a balance: too few iterations may result in directional information failing to fully traverse the physical gaps of the longitudinal beams, making the directional field in the gap regions unreliable; too many iterations will significantly increase computation time and may lead to over-smoothing. In this embodiment, the number of iterations is set to 5. Implementers can adjust the number of iterations according to the actual implementation situation. For example, when the gaps between the longitudinal beams to be processed are large or the noise is strong, the number of iterations can be appropriately increased, such as 5 to 10, to ensure sufficient convergence of the directional field; if the longitudinal beam continuity is good and the gaps are small, the number of iterations can be reduced, such as 3, to improve efficiency.

[0043] S3. Obtain the normal vector of the target pixel based on the final direction vector of the target pixel; obtain the axis positioning score of the target pixel based on the divergence of the normal vector of the target pixel, and assemble the axis positioning scores of all pixels into an axis positioning map.

[0044] It should be noted that, in obtaining a continuous final direction field Subsequently, in order to find the main centerline of the longitudinal beam and complete the longitudinal beam straightness detection, this invention generates a scalar map so that the pixels located on the main centerline of the longitudinal beam have the highest response value.

[0045] Within the longitudinal beam region, due to its straight structure, the normal vectors at all points point in the same direction and have the same magnitude. Therefore, the normal vector field in this region is constant, and its divergence is zero. However, at the two edges of the longitudinal beam, i.e., the region transitioning from the longitudinal beam to the background, the normal vectors undergo a sharp and opposite change in direction. This creates a region with positive divergence on one edge and a region with negative divergence on the other edge. The main central axis of the longitudinal beam is located precisely in the middle of these two extreme divergence zones. By utilizing this characteristic, the present invention can accurately locate the main central axis of the longitudinal beam.

[0046] Specifically, for target pixels Obtain the axis positioning score. The axis positioning score of the target pixel satisfies the expression:

[0047] in, Represents the target pixel. Represents the target pixel. The axis positioning score; and express Within the central supersized neighborhood window, there are two sub-neighborhood windows separated by the line to which the final direction vector of the target pixel belongs; Represents a sub-neighborhood window Pixels within; Represents a sub-neighborhood window Pixels within; and Representing pixels and The normal vector of a pixel is obtained by rotating the final direction vector of the pixel clockwise by 90°. This represents the divergence.

[0048] More specifically, using image processing software, open one or more representative images of the longitudinal beam, ensuring the beam area is clearly visible in the image. Use the software's measurement tool to measure the vertical pixel distance between the two edges of the beam. Perform multiple measurements at different locations in the image, such as the upper, middle, and lower parts of the beam. Then calculate the average of these measurements as the expected width of the beam. In this embodiment, the image processing software uses an interactive window from OpenCV, and the measurement tool uses a ruler tool. The implementer can choose the appropriate image processing software and measurement tool based on the actual situation.

[0049] The diameter of the oversized neighborhood window should be larger than the maximum expected width of the longitudinal beam being measured in the image. In this embodiment, the expected width is used. The core requirement for setting the diameter of the oversized neighborhood window is that it must be larger than the maximum expected width of the measured longitudinal beam in the image. This is because the calculation of the axis positioning score relies on capturing the divergence extrema bands that are symmetrically positive and negative at the edges of the longitudinal beam. If the diameter of the oversized neighborhood window is smaller than the width of the longitudinal beam, the two half-neighborhood windows will not be able to simultaneously and completely contain the divergence responses on both sides when calculating the score, leading to the failure of the main central axis positioning. Choosing 1.5 times instead of exactly 1.0 times is to provide a safety margin, ensuring that the method still works reliably even if the actual width of the longitudinal beam in the image is slightly larger than the expected width. If the width of the longitudinal beam varies greatly or the expected width is inaccurate, a larger multiple, such as 2.0 times, may be needed to ensure robustness.

[0050] More specifically, when the target pixel is located exactly on the main central axis of the longitudinal beam, its oversized neighborhood window is divided into two halves: a half-neighborhood window. The entire divergence response band generated by one side edge will be negative, and the sum of its divergences will be a negative number with a large absolute value; while the other half of the neighborhood window The positive divergence response band completely encompassing the other edge is summed to a large positive number. Multiplying these two results in a large negative number, which is then inverted to make... It becomes a very large positive value. When the center pixel... When the line deviates from the main central axis, the dividing line shifts accordingly. For example, if... Towards If one side moves, then The mixture will contain some regions of positive divergence, causing the absolute value of its sum to decrease, while... This may result in the loss of some positive divergence regions, reducing the sum of these regions and causing a significant decrease in the absolute value of the product. The value also decreases accordingly. Therefore, the target pixel will only generate the maximum axis localization score at the position that maximizes the product of the sum of the divergences on both sides of the neighborhood window, i.e., on the main central axis.

[0051] The axis localization scores of all pixels in the image constitute the axis localization map. The axis positioning diagram appears as a bright, continuous response band, with its ridgeline precisely corresponding to the main centerline of the longitudinal beam.

[0052] S4. Extract the main centerline skeleton point set of the axis positioning diagram and fit it into a straight line using the least squares method. Calculate the error from the skeleton point to the fitted straight line. Compare the error with the preset tolerance to determine whether the installation quality of the middle part of the belt conveyor is qualified.

[0053] It should be noted that the present invention uses an axis positioning diagram. The geometric information contained therein is transformed into quantitative straightness assessment results.

[0054] Specifically, the axis positioning image is binarized, converting the high-brightness, wide response band into a binary image. A morphological skeleton extraction algorithm is applied to this binary image, iteratively stripping pixels from the region edges until the wide binary image is thinned into a single-pixel-width main central axis skeleton. Connected component analysis is performed on the thinned skeleton image, retaining the longest skeleton line segment as the skeleton point set of the main central axis. The extracted main central axis skeleton point set is then fitted with a line using the least squares method to obtain a mathematical straight line that best represents the main central axis of the longitudinal beam. The perpendicular distance from each skeleton point to the fitted line is calculated, and the root mean square (RMS) value of all these distances is used as the error in the straightness of the longitudinal beam. In this embodiment, the morphological skeleton extraction algorithm uses the Zhang-Suen thinning algorithm, with a length threshold of 150 pixels. Implementers can choose the morphological skeleton extraction algorithm and length threshold according to actual needs.

[0055] Furthermore, the calculated straightness error is compared with the preset tolerance standard. If the error is less than or equal to the tolerance, the installation quality of the middle part of the belt conveyor is deemed qualified; if the error is greater than the tolerance, the installation quality of the middle part of the belt conveyor is deemed unqualified.

[0056] This completes a method for inspecting the installation quality of the middle section of a belt conveyor.

[0057] This invention also discloses a belt conveyor intermediate section installation quality inspection system, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, a belt conveyor intermediate section installation quality inspection method according to the present invention is implemented.

[0058] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

Claims

1. A method for inspecting the installation quality of the middle section of a belt conveyor, characterized in that, include: Obtain a grayscale image of the middle section of the belt conveyor; denote any pixel in the grayscale image as the target pixel. After applying a window function to the neighborhood window of the target pixel, the initial direction vector of the target pixel is obtained based on Fourier transform; Based on the distance between the target pixel and its neighboring window pixels and the similarity of the initial direction vectors of the target pixel and its neighboring window pixels, the anisotropic kernel function between the target pixel and its neighboring window pixels is obtained. The anisotropic kernel function is used to iteratively update the initial direction vector of the target pixel to obtain the final direction vector of the target pixel. The normal vector of the target pixel is obtained from the final direction vector of the target pixel; the axis localization score of the target pixel is obtained from the divergence of the normal vector of the target pixel; and the axis localization scores of all pixels are combined to form an axis localization map. Extract the main centerline skeleton point set of the axis positioning diagram and fit it into a straight line using the least squares method. Calculate the error from the skeleton point to the fitted straight line. Compare the error with the preset tolerance to determine whether the installation quality of the middle part of the belt conveyor is qualified.

2. The method for inspecting the installation quality of the middle section of a belt conveyor according to claim 1, characterized in that, The application of a window function to the neighborhood window of the target pixel includes: Apply the Hanning window function to the neighborhood window of the target pixel.

3. The method for inspecting the installation quality of the middle section of a belt conveyor according to claim 1, characterized in that, The anisotropic kernel function between the target pixel and its neighboring window pixels satisfies the expression: ； in, Represents the target pixel. Its neighboring window pixels Anisotropic kernel function values ​​between; Indicates the target pixel; Represents the pixels of the neighboring window; It is the number of iterations; Represents pixels In the The direction vector at the next iteration; Represents pixels In the The direction vector at the next iteration; Indicates the first hyperparameter; Indicates the second hyperparameter; Represents the dot product operation of vectors; Represents the natural exponential function; Represents the absolute value symbol.

4. The method for inspecting the installation quality of the middle section of a belt conveyor according to claim 3, characterized in that, The first hyperparameter is set to 0.

8.

5. A method for inspecting the installation quality of the middle section of a belt conveyor according to claim 3, characterized in that, The second hyperparameter is set to 2.

0.

6. A method for inspecting the installation quality of the middle section of a belt conveyor according to claim 1, characterized in that, The step of obtaining the normal vector of the target pixel based on the final direction vector of the target pixel includes: Rotate the final direction vector of the target pixel 90° clockwise to obtain the normal vector of the target pixel.

7. A method for inspecting the installation quality of the middle section of a belt conveyor according to claim 1, characterized in that, The axis positioning score of the target pixel satisfies the expression: ； in, Represents the target pixel. Represents the target pixel. The axis positioning score; and express Within a central oversized neighborhood window, two sub-neighborhood windows are defined by the line representing the final direction vector of the target pixel. These oversized neighborhood windows are defined by the expected width of the longitudinal beam. A neighborhood window whose side length is twice that of the neighborhood window; Represents a sub-neighborhood window Pixels within; Represents a sub-neighborhood window Pixels within; and Representing pixels normal vector and pixel The normal vector; This represents the divergence.

8. A method for inspecting the installation quality of the middle section of a belt conveyor according to claim 1, characterized in that, Extracting the main centerline skeleton point set of the axis positioning map, including: The axis positioning map is binarized to obtain a binary image; a morphological skeleton extraction algorithm is applied to the binary image to obtain a main central axis skeleton with a single pixel width; connected component analysis is performed on the thinned main central axis skeleton, and the longest main central axis skeleton line segment is retained as the skeleton point set of the main central axis.

9. A method for inspecting the installation quality of the middle section of a belt conveyor according to claim 1, characterized in that, The error from the skeleton point to the fitted line is calculated; The installation quality of the middle section of the belt conveyor is determined by comparing the error with the preset tolerance, including: The error between the skeleton points and the fitted line is the root mean square of the perpendicular distances from all skeleton points to the fitted line. When the root mean square is less than or equal to the preset tolerance, the installation quality is deemed acceptable; when it is greater than the preset tolerance, the installation quality is deemed unacceptable.

10. A quality inspection system for the intermediate section of a belt conveyor, characterized in that, include: A processor and a memory, the memory storing computer program instructions that, when executed by the processor, implement a method for detecting the installation quality of the intermediate section of a belt conveyor according to any one of claims 1-9.

Images