Method and system for cleaning foreign matters on coal conveying belt based on visual features

Abstract

The invention provides a coal conveying belt foreign matter cleaning method and system based on visual features, and relates to the technical field of computer vision. The method comprises the following steps: acquiring an original image of a coal conveying belt by installing a camera; carrying out analysis processing on the original image, and determining a Gramb angle sum field image and a Gramb angle difference field image; determining a comprehensive descriptor of the foreign matter on the surface of the coal conveying belt according to the original image, the Gramb angle sum field image and the Gramb angle difference field image; inputting the comprehensive descriptor into a classifier to obtain a foreign matter recognition result; according to the foreign matter recognition result, whether a cleaning device is started for cleaning or not is determined; if the cleaning device is started for cleaning, after the cleaning device completes cleaning, the cleaning effect is fed back until no foreign matter exists on the surface of the belt. According to the method, the image pixel relation and the self-adaptive weight can be considered through the Grubrum angle field and the Grubrum difference field, the accuracy of description of the foreign matter on the coal conveying belt is improved, and the recognition result is optimized.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and in particular to a method and system for cleaning foreign matter from a coal conveyor belt based on visual features. Background Art

[0002] In the related technology, CN115180367A discloses a belt conveyor foreign object identification device, which relates to the technical field of conveyor belt foreign object identification, including a detection component that detects foreign objects on the conveyor belt through a detection camera, a mobile shell is provided on the detection component, and a picking component for processing foreign objects on the belt is provided in the mobile shell, and two groups of sliding plates are provided in the picking component, and foreign objects on the belt are picked up by moving the sliding plates. A fire extinguishing component for cooling and extinguishing coal is also provided in the mobile shell, and the fire extinguishing component can detect the temperature of the coal on the belt, and when high-temperature coal is detected, the fire extinguishing gas is mixed in advance and the coal on the belt is sprayed, and a driving component is provided in the mobile shell, and the driving component changes the picking speed of the picking component and the mixing speed of the fire extinguishing component. This scheme can automatically detect and pick up foreign objects on the belt, and can avoid fires caused by excessively high coal temperature on the belt.

[0003] CN117184812A discloses a method for detecting tearing and foreign matter of a conveyor belt, the method comprising: preprocessing the image collected by the image acquisition device; identifying the preprocessed belt image through a pre-established belt tearing and foreign matter identification detection model to complete belt tearing detection and foreign matter identification; the belt tearing and foreign matter identification detection model adopts a Retinex-based image enhancement method and realizes multi-scale target detection according to the detection idea of ​​the image feature pyramid. This scheme can reduce the belt tear length to the greatest extent, has a great promoting effect on the optimization and improvement of the converter process, and has huge economic benefits and production significance.

[0004] Therefore, in the related technologies, although image processing technology is used to identify foreign objects, the related technologies often only perform feature analysis on the original images. In the complex and changeable mining environment, affected by factors such as light and dust, the recognition accuracy is not high, and the feature performance differences are not taken into account. That is, there are defects such as inaccuracy in image description and static nature of feature weights.

[0005] The information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0006] The present invention provides a method and system for cleaning foreign matter from a coal conveyor belt based on visual features, which can solve the technical problems of the defects of inaccuracy of image description and static nature of feature weights in related technologies.

[0007] According to a first aspect of the present invention, a method for cleaning foreign matter from a coal conveyor belt based on visual features is provided, comprising: By installing a camera, the original image of the coal conveyor belt is obtained; Analyzing and processing the original image to determine a Gram angle sum field image and a Gram angle difference field image; Determining a comprehensive descriptor of foreign matter on the surface of the coal conveyor belt according to the original image, the Gram angle sum field image and the Gram angle difference field image; Inputting the comprehensive descriptor into a classifier to obtain a foreign body recognition result; Determining whether to start a cleaning device for cleaning according to the foreign object identification result; If the cleaning device is started for cleaning, the cleaning device will provide feedback on the cleaning effect after completing the cleaning until there is no foreign matter on the belt surface.

[0008] Further, the original image is analyzed and processed to determine the Gram angle sum field image and the Gram angle difference field image, including: Expanding the original image to obtain an expanded image; Evenly divide each channel of the expanded image to obtain 9 segmented images; Determining a statistical descriptor based on the segmented image; Based on the statistical descriptors, a Gram angle sum field image and a Gram angle difference field image are determined.

[0009] Further, determining a statistical descriptor according to the segmented image includes: Calculate the maximum, minimum, mean, mode, median, range, variance and standard deviation for each segmented image; According to the formula Determine the description vector of the vth segmented image ,in, is the maximum value of the vth segmented image, is the minimum value of the vth segmented image, is the mean of the vth segmented image, is the mode of the vth segmented image, is the median of the vth segmented image, is the range of the vth segmented image, is the variance of the vth segmented image, is the standard deviation of the vth segmented image, v≤9, and v is a positive integer; The description vectors of the segmented image are combined in a hierarchical combination manner, wherein the first-level combination forms four different first-level description vectors according to four different combination methods, and the second-level combination forms a statistical descriptor according to the result of the first-level combination; According to the formula Determine statistical descriptors ,in, and are 4 different first-level description vectors, and are the description vectors of the vth segmented image respectively.

[0010] Further, determining the Gram angle sum field image and the Gram angle difference field image according to the statistical descriptor comprises: According to the formula Get the normalized vector The i-th dimension of , where n is the dimension of the statistical descriptor, is a statistical descriptor The component of the i-th dimension of , where i and n are both positive integers; According to the formula , , Determine Gram angle and field image and Gram angle difference image ,in, for The cosine of the angle, for The corresponding radius, for The corresponding timestamp, M is the normalization factor, They are The cosine of the angle , i≤n, j≤n, and j is a positive integer.

[0011] Further, a comprehensive descriptor of foreign matter on the surface of the coal conveyor belt is determined according to the original image, the Gram angle sum field image and the Gram angle difference field image, including: Obtaining original image features, Gram angle difference field features and Gram angle sum field features according to the original image, the Gram angle sum field image and the Gram angle difference field image; Determining original image feature weights, Gram angle and field feature weights, and Gram angle difference field feature weights according to the original image feature, the Gram angle and field feature, and the Gram angle difference field feature; A comprehensive descriptor of foreign matter on the surface of the coal conveyor belt is determined based on the original image features, the Gram angle and field features, the Gram angle difference field features, the original image feature weights, the Gram angle and field feature weights and the Gram angle difference field feature weights.

[0012] Further, according to the original image feature, the Gram angle and field feature and the Gram angle difference field feature, determining the original image feature weight, the Gram angle and field feature weight and the Gram angle difference field feature weight, including: , , , , , , , , , ,

[0013] Determining Gram Angles and Field Characteristic Weights , original image feature weight Gram difference field feature weight ,in, is the decision matrix, are the Gram angle and field characteristics, Original image features, is the Gram angle difference field characteristic, is the value of the xth row and yth column of the standardized decision matrix, is the value of the decision matrix in row x and column y, is the value of the yth column of the decision matrix, , , …, are the components of vector E, is the information entropy of the yth column of the standardized decision matrix, E is the entropy vector, is the normalized information entropy weight of the yth column of the standardized decision matrix, is the weighted decision matrix, is the value of the 1st, 2nd, …, mth columns of the standardized decision matrix, is the normalized information entropy weight of the 1st, 2nd, …, mth columns of the standardized decision matrix, The value of the positive ideal solution in the yth column of the weighted decision matrix, is the value of the negative ideal solution in the yth column of the weighted decision matrix, , and are the values ​​of the 1st, 2nd and 3rd rows of the weighted decision matrix, is the value of the xth row and yth column of the weighted decision matrix, is the distance to the positive ideal solution in the xth row of the weighted decision matrix, is the distance to the negative ideal solution of the x-th row of the weighted decision matrix, is the feature weight of the x-th row of the decision matrix, m is the number of decision matrix columns, x≤3, y≤m, and x, y and m are all positive integers, max is the maximum value function, and min is the minimum value function.

[0014] Further, according to the original image feature, the Gram angle sum field feature, the Gram angle difference field feature, the original image feature weight, the Gram angle sum field feature weight and the Gram angle difference field feature weight, a comprehensive descriptor of foreign matter on the surface of the coal conveyor belt is determined, including: According to the formula A comprehensive descriptor F for determining foreign matter on the surface of coal conveyor belts.

[0015] According to a second aspect of the present invention, a visual feature coal conveyor belt foreign body cleaning system is provided, comprising: The original image module is used to obtain the original image of the coal conveyor belt by installing a camera; A Gram angle sum field image and a Gram angle difference field image module, used for analyzing and processing the original image to determine a Gram angle sum field image and a Gram angle difference field image; A comprehensive descriptor module, for determining a comprehensive descriptor of foreign matter on the surface of the coal conveyor belt according to the original image, the Gram angle sum field image and the Gram angle difference field image; A foreign body identification result module, used for inputting the comprehensive descriptor into a classifier to obtain a foreign body identification result; A judgment module, used to determine whether to start a cleaning device for cleaning according to the foreign object recognition result; The feedback module is used to feedback the cleaning effect after the cleaning device is started to clean until there is no foreign matter on the belt surface.

[0016] Technical effect: According to the present invention, the image pixel relationship is considered by using the Gram angle field and the Gram angle difference field, which improves the accuracy of the description of foreign bodies on the coal conveyor belt. The adaptive weight strategy enables the weight of a single feature to be dynamically updated with the recognition image, further optimizing the robustness and accuracy of the recognition result. When determining the Gram angle sum field image and the Gram angle difference field image, the statistical feature extraction of the original image can be performed in multiple dimensions to effectively capture the various attributes of foreign bodies on the coal conveyor belt, providing rich information for subsequent recognition. By mapping the statistical features to a two-dimensional image, the Gram angle sum field and the Gram angle difference field are generated, and the efficient representation of the original image features is achieved, thereby significantly improving the accuracy of foreign body recognition. When determining the comprehensive descriptor of foreign bodies on the surface of the coal conveyor belt, the features of the original image, the Gram angle sum field image and the Gram angle difference field image can be fused, and the features can be dynamically weighted in combination with the adaptive weighting method, so that the comprehensive descriptor can better reflect the essential characteristics of the foreign body, thereby enhancing the representativeness of the comprehensive descriptor, effectively coping with the changes of foreign bodies in different scenes, and improving the stability and reliability of the recognition effect.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only and do not limit the present invention. Other features and aspects of the present invention will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other embodiments can be obtained based on these drawings without creative work. Figure 1 A schematic diagram showing a flow chart of a method for cleaning foreign matter from a coal conveyor belt according to visual features of an embodiment of the present invention; Figure 2 An analysis engineering flow chart of a coal conveyor belt foreign body cleaning system according to visual features of an embodiment of the present invention is exemplarily shown; Figure 3 A feature engineering flow chart of a coal conveyor belt foreign body cleaning system according to visual features of an embodiment of the present invention is exemplarily shown; Figure 4 A block diagram of a coal conveyor belt foreign matter cleaning system based on visual features according to an embodiment of the present invention is exemplarily shown. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0021] Figure 1 A schematic flow chart of a method for cleaning foreign matter from a coal conveyor belt according to visual features of an embodiment of the present invention is exemplarily shown, the method comprising: Step S101, obtaining an original image of the coal conveyor belt by installing a camera; Step S102, analyzing and processing the original image to determine a Gram angle sum field image and a Gram angle difference field image; Step S103, determining a comprehensive descriptor of foreign matter on the surface of the coal conveyor belt according to the original image, the Gram angle sum field image and the Gram angle difference field image; Step S104, inputting the comprehensive descriptor into a classifier to obtain a foreign body recognition result; Step S105, determining whether to start a cleaning device for cleaning according to the foreign object identification result; Step S106, if the cleaning device is started to clean, the cleaning device will feedback the cleaning effect after completing the cleaning until there is no foreign matter on the belt surface.

[0022] According to the method for cleaning foreign objects from a coal conveyor belt based on visual features of an embodiment of the present invention, the accuracy of describing foreign objects on the coal conveyor belt is improved by considering the relationship between image pixels through the Gram angle field and the Gram difference field. The adaptive weight strategy enables the weight of a single feature to be dynamically updated with the recognized image, further optimizing the robustness and accuracy of the recognition result.

[0023] According to one embodiment of the present invention, in step S101, a camera device is installed so that the camera can clearly capture the operation status of the coal conveyor belt and obtain the original image of the coal conveyor belt in real time.

[0024] According to an embodiment of the present invention, in step S102, the original image is analyzed and processed to determine the Gram angle sum field image and the Gram angle difference field image.

[0025] According to one embodiment of the present invention, step S102 includes: expanding the original image to obtain an expanded image; evenly dividing each channel of the expanded image to obtain 9 segmented images; determining a statistical descriptor based on the segmented image; and determining a Gram angle sum field image and a Gram angle difference field image based on the statistical descriptor.

[0026] According to one embodiment of the present invention, Figure 2 The analysis engineering flow chart of the coal conveyor belt foreign body cleaning system according to the visual features of an embodiment of the present invention is exemplarily shown, and the original image is expanded, and the original image is recorded as Img, and the size is , is the width of the original image, is the length of the original image, is the number of channels of the original image, the amount of expansion in the width w direction and the length h direction and , add pixel value 0 to the filling area to obtain the expanded image, the size of the expanded image is Each channel of the expanded image is evenly divided to obtain 9 segmented images, and statistical descriptors are calculated. The Gram angle sum field image and Gram angle difference field image are obtained by using the GAF technique.

[0027] According to one embodiment of the present invention, based on the segmented image, determining the statistical descriptor includes: calculating the maximum value, minimum value, mean value, mode, median, range, variance and standard deviation for each segmented image; determining the description vector of the vth segmented image according to formula (1): , (1) Among them, is the maximum value of the vth segmented image, is the minimum value of the vth segmented image, is the mean of the vth segmented image, is the mode of the vth segmented image, is the median of the vth segmented image, is the range of the vth segmented image, is the variance of the vth segmented image, is the standard deviation of the vth segmented image, v≤9, and v is a positive integer; the description vectors of the segmented images are combined in a hierarchical combination manner, the first-level combination is composed of 4 different first-level description vectors according to 4 different combination methods, and the second-level combination is composed of a statistical descriptor according to the result of the first-level combination; the statistical descriptor is determined according to formulas (2), (3), (4), (5) and (6) , (2), (3), (4), (5), (6), in, and are 4 different first-level description vectors, and are the description vectors of the vth segmented image respectively.

[0028] According to one embodiment of the present invention, for each segmented image, statistics are calculated, description vectors are constructed, and the final statistical descriptor is formed by hierarchically combining the description vectors. Four different combination methods of the first-level combination are given in formulas (2), (3), (4) and (5). arrive The statistical descriptor contains the information of all first-level description vectors.

[0029] According to an embodiment of the present invention, determining the Gram angle sum field image and the Gram angle difference field image according to the statistical descriptor includes: obtaining a normalized vector according to formula (7) The i-th dimension of , (7), where n is the dimension of the statistical descriptor, is a statistical descriptor The component of the i-th dimension of , and i and n are both positive integers; according to formulas (8), (9) and (10), the Gram angle and field image are determined and Gram angle difference image , (8), (9), (10), where for The cosine of the angle, for The corresponding radius, for The corresponding timestamp, M is the normalization factor, They are The cosine of the angle , i≤n, j≤n, and j is a positive integer.

[0030] According to one embodiment of the present invention, the statistical descriptor is normalized and scaled to between [-1, 1] to obtain a normalized vector The i-th dimension of In polar coordinates, the normalized vector Encoding, based on different formulas, can generate Gram angle and field image and Gram angle difference image .

[0031] In this way, the statistical features of the original image can be extracted through multiple dimensions, effectively capturing the various attributes of foreign objects on the coal conveyor belt, providing rich information for subsequent identification. By mapping the statistical features to a two-dimensional image, the Gram angle sum field and Gram angle difference field are generated, and efficient representation of the original image features is achieved, thereby significantly improving the accuracy of foreign object identification.

[0032] According to one embodiment of the present invention, in step S103, a comprehensive descriptor of foreign matter on the surface of the coal conveyor belt is determined based on the original image, the Gram angle sum field image and the Gram angle difference field image.

[0033] According to one embodiment of the present invention, step S103 includes: obtaining original image features, Gram angle difference field features and Gram angle sum field features according to the original image, the Gram angle sum field image and the Gram angle difference field image; determining original image feature weights, Gram angle sum field feature weights and Gram angle difference field feature weights according to the original image features, the Gram angle sum field features and the Gram angle difference field features; determining a comprehensive descriptor of foreign matter on the surface of the coal conveyor belt according to the original image features, the Gram angle sum field features, the Gram angle difference field features, the original image feature weights, the Gram angle sum field feature weights and the Gram angle difference field feature weights.

[0034] According to one embodiment of the present invention, Figure 3 The feature engineering flow chart of the coal conveyor belt foreign body cleaning system based on the visual features of an embodiment of the present invention is exemplarily shown, and the original image features, Gram angle and field features, and Gram angle difference field features are extracted from the original image, the Gram angle and field image, and the Gram angle difference field image, respectively. The feature represents the information of the image under different dimensions and transformations, which is helpful for subsequent analysis and processing. Based on the three features extracted above, namely, the original image features, the Gram angle and field features, and the Gram angle difference field features, the respective feature weights are further determined. The feature weight reflects the importance and contribution of each feature when constructing a comprehensive descriptor. The comprehensive descriptor is a composite representation that integrates multiple feature information, which can more comprehensively and accurately reflect the characteristics of foreign bodies on the surface of the coal conveyor belt. Through the comprehensive descriptor, foreign bodies can be detected and identified more effectively.

[0035] According to an embodiment of the present invention, according to the original image feature, the Gram angle and field feature and the Gram angle difference field feature, the original image feature weight, the Gram angle and field feature weight and the Gram angle difference field feature weight are determined, including: determining the Gram angle and field feature weight according to formulas (11), (12), (13), (14), (15), (16), (17), (18), (19), (20) and (21) , original image feature weight Gram difference field feature weight , (11), (12), (13), (14), (15), (16), (17), (18), (19), (20), (twenty one), in, is the decision matrix, are the Gram angle and field characteristics, Original image features, is the Gram angle difference field characteristic, is the value of the xth row and yth column of the standardized decision matrix, is the value of the decision matrix in row x and column y, is the value of the yth column of the decision matrix, , , …, are the components of vector E, is the information entropy of the yth column of the standardized decision matrix, E is the entropy vector, is the normalized information entropy weight of the yth column of the standardized decision matrix, is the weighted decision matrix, is the value of the 1st, 2nd, …, mth columns of the standardized decision matrix, is the normalized information entropy weight of the 1st, 2nd, …, mth columns of the standardized decision matrix, The value of the positive ideal solution in the yth column of the weighted decision matrix, is the value of the negative ideal solution in the yth column of the weighted decision matrix, , and are the values ​​of the 1st, 2nd and 3rd rows of the weighted decision matrix, is the value of the xth row and yth column of the weighted decision matrix, is the distance to the positive ideal solution in the xth row of the weighted decision matrix, is the distance to the negative ideal solution of the x-th row of the weighted decision matrix, is the feature weight of the x-th row of the decision matrix, m is the number of decision matrix columns, x≤3, y≤m, and x, y and m are all positive integers, max is the maximum value function, and min is the minimum value function.

[0036] According to one embodiment of the present invention, a decision matrix is ​​constructed by using original image features, Gram angle sum field features and Gram angle difference field features, the decision matrix is ​​standardized to obtain a standardized decision matrix, the information entropy of each column of the standardized decision matrix is ​​calculated based on the standardized decision matrix, an entropy vector is constructed based on the information entropy, the information entropy weight of each column of the standardized decision matrix is ​​calculated, and the information entropy weight is normalized to obtain a normalized information entropy weight, each standardized element is multiplied by its corresponding normalized information entropy weight to obtain a weighted decision matrix, the value of the positive ideal solution and the value of the negative ideal solution of each column of the weighted decision matrix are calculated, based on the value of the positive ideal solution and the value of the negative ideal solution, the distance of the positive ideal solution and the distance of the negative ideal solution of each row of the weighted decision matrix are calculated, and finally the weight of the feature of each row of the decision matrix is ​​calculated and normalized.

[0037] According to an embodiment of the present invention, a comprehensive descriptor of foreign matter on the surface of a coal conveyor belt is determined according to the original image feature, the Gram angle sum field feature, the Gram angle difference field feature, the original image feature weight, the Gram angle sum field feature weight and the Gram angle difference field feature weight, including: determining a comprehensive descriptor F of foreign matter on the surface of a coal conveyor belt according to formula (22), (twenty two); According to one embodiment of the present invention, each feature is weighted by its corresponding feature weight, and each weighted feature is normalized by its sum, thereby obtaining a comprehensive descriptor.

[0038] In this way, the features of the original image, the Grammar angle sum field image and the Grammar angle difference field image can be fused, and the features can be dynamically weighted in combination with the adaptive weighting method, so that the comprehensive descriptor can better reflect the essential characteristics of the foreign matter, thereby enhancing the representativeness of the comprehensive descriptor, effectively coping with the changes of foreign matter in different scenarios, and improving the stability and reliability of the recognition effect.

[0039] According to one embodiment of the present invention, in step S104, the comprehensive descriptor integrates the original image features, the Gram angle and field features, and the Gram angle difference field features, and the features are all assigned corresponding feature weights according to their importance. Therefore, the comprehensive descriptor comprehensively and accurately describes the image information of the surface of the coal conveyor belt, especially the potential foreign matter features, and passes the comprehensive descriptor as input to a pre-trained classifier, which is a neural network model with the ability to learn and recognize patterns from input data. The classifier will output a foreign matter recognition result. The foreign matter recognition result is usually a label or a set of probability values, which clearly indicates whether there is a foreign matter in the image and the specific type of the foreign matter.

[0040] According to one embodiment of the present invention, in step S105, coal is often mixed with large pieces of gangue, anchor rods and other foreign objects during transportation. If the foreign objects are large, hard objects such as large pieces of gangue and anchor rods, they will cause serious interference or even damage to the operation of the belt. Therefore, it is necessary to immediately start the cleaning device to remove them so that the belt can operate normally and the coal can be transported smoothly.

[0041] According to one embodiment of the present invention, in step S106, after the cleaning device completes the first cleaning, steps S101 to S105 can be repeated to obtain the foreign object identification result again, so as to evaluate the effect, that is, to determine whether to start the cleaning device to clean until there is no foreign object on the belt surface.

[0042] According to the method for cleaning foreign bodies from a coal conveyor belt based on visual features of an embodiment of the present invention, the accuracy of describing foreign bodies on the coal conveyor belt is improved by considering the image pixel relationship through the Gram angle field and the Gram angle difference field. The adaptive weight strategy enables the weight of a single feature to be dynamically updated with the recognized image, further optimizing the robustness and accuracy of the recognition result. When determining the Gram angle sum field image and the Gram angle difference field image, the statistical feature extraction of the original image can be performed in multiple dimensions to effectively capture the various attributes of foreign bodies on the coal conveyor belt, providing rich information for subsequent recognition. By mapping the statistical features to a two-dimensional image, the Gram angle sum field and the Gram angle difference field are generated, and the efficient representation of the original image features is achieved, thereby significantly improving the accuracy of foreign body recognition. When determining the comprehensive descriptor of foreign bodies on the surface of the coal conveyor belt, the features of the original image, the Gram angle sum field image and the Gram angle difference field image can be fused, and the features can be dynamically weighted in combination with the adaptive weighting method, so that the comprehensive descriptor can better reflect the essential characteristics of the foreign bodies, thereby enhancing the representativeness of the comprehensive descriptor, effectively coping with the changes of foreign bodies in different scenes, and improving the stability and reliability of the recognition effect.

[0043] Figure 4 A block diagram of a coal conveyor belt foreign body cleaning system according to visual features of an embodiment of the present invention is exemplarily shown, the system comprising: The original image module is used to obtain the original image of the coal conveyor belt by installing a camera; A Gram angle sum field image and a Gram angle difference field image module, used for analyzing and processing the original image to determine a Gram angle sum field image and a Gram angle difference field image; A comprehensive descriptor module, for determining a comprehensive descriptor of foreign matter on the surface of the coal conveyor belt according to the original image, the Gram angle sum field image and the Gram angle difference field image; A foreign body identification result module, used for inputting the comprehensive descriptor into a classifier to obtain a foreign body identification result; A judgment module, used to determine whether to start a cleaning device for cleaning according to the foreign object recognition result; The feedback module is used to feedback the cleaning effect after the cleaning device is started to clean until there is no foreign matter on the belt surface.

[0044] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0045] It should be understood by those skilled in the art that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may be deformed or modified in any way without departing from the principles.

Claims

1. A method for cleaning foreign matter from a coal conveyor belt based on visual features, characterized in that: include: By installing a camera, the original image of the coal conveyor belt is obtained; Analyzing and processing the original image to determine a Gram angle sum field image and a Gram angle difference field image; Determining a comprehensive descriptor of foreign matter on the surface of the coal conveyor belt according to the original image, the Gram angle sum field image and the Gram angle difference field image; Inputting the comprehensive descriptor into a classifier to obtain a foreign body recognition result; Determining whether to start a cleaning device for cleaning according to the foreign object identification result; If the cleaning device is started for cleaning, the cleaning device will provide feedback on the cleaning effect after completing the cleaning until there is no foreign matter on the belt surface.

2. The method for cleaning foreign matter from a coal conveyor belt based on visual characteristics according to claim 1 is characterized in that: Analyzing and processing the original image to determine the Gram angle sum field image and the Gram angle difference field image, including: Expanding the original image to obtain an expanded image; Evenly divide each channel of the expanded image to obtain 9 segmented images; Determining a statistical descriptor based on the segmented image; Based on the statistical descriptors, a Gram angle sum field image and a Gram angle difference field image are determined.

3. The method for cleaning foreign matter from a coal conveyor belt based on visual characteristics according to claim 2 is characterized in that: Determining a statistical descriptor according to the segmented image includes: Calculate the maximum, minimum, mean, mode, median, range, variance and standard deviation for each segmented image; According to the formula , Determine the description vector of the vth segmented image ,in, is the maximum value of the vth segmented image, is the minimum value of the vth segmented image, is the mean of the vth segmented image, is the mode of the vth segmented image, is the median of the vth segmented image, is the range of the vth segmented image, is the variance of the vth segmented image, is the standard deviation of the vth segmented image, v≤9, and v is a positive integer; The description vectors of the segmented image are combined in a hierarchical combination manner, wherein the first-level combination forms four different first-level description vectors according to four different combination methods, and the second-level combination forms a statistical descriptor according to the result of the first-level combination; According to the formula , Determine statistical descriptors ,in, and are 4 different first-level description vectors, and are the description vectors of the vth segmented image respectively.

4. The method for cleaning foreign matter from a coal conveyor belt based on visual characteristics according to claim 3 is characterized in that: Determining a Gram angle sum field image and a Gram angle difference field image according to the statistical descriptor comprises: According to the formula Get the normalized vector The i-th dimension of , where n is the dimension of the statistical descriptor, is a statistical descriptor The component of the i-th dimension of , where i and n are both positive integers; According to the formula , , Determine Gram angle and field image and Gram angle difference image ,in, for The cosine of the angle, for The corresponding radius, for The corresponding timestamp, M is the normalization factor, They are The cosine of the angle , i≤n, j≤n, and j is a positive integer.

5. The method for cleaning foreign matter from a coal conveyor belt based on visual characteristics according to claim 1 is characterized in that: Determining a comprehensive descriptor of foreign matter on the surface of the coal conveyor belt according to the original image, the Gram angle sum field image and the Gram angle difference field image, including: Obtaining original image features, Gram angle difference field features and Gram angle sum field features according to the original image, the Gram angle sum field image and the Gram angle difference field image; Determining original image feature weights, Gram angle and field feature weights, and Gram angle difference field feature weights according to the original image feature, the Gram angle and field feature, and the Gram angle difference field feature; A comprehensive descriptor of foreign matter on the surface of the coal conveyor belt is determined based on the original image features, the Gram angle and field features, the Gram angle difference field features, the original image feature weights, the Gram angle and field feature weights and the Gram angle difference field feature weights.

6. The method for cleaning foreign matter from a coal conveyor belt based on visual characteristics according to claim 5 is characterized in that: Determining original image feature weights, Gram angle and field feature weights, and Gram angle difference field feature weights according to the original image feature, the Gram angle and field feature, and the Gram angle difference field feature weights, including: According to the formula , , , , , , , , , , Determining Gram Angles and Field Characteristic Weights , original image feature weight Gram difference field feature weight ,in, is the decision matrix, are the Gram angle and field characteristics, Original image features, is the Gram angle difference field characteristic, is the value of the xth row and yth column of the standardized decision matrix, is the value of the decision matrix in row x and column y, is the value of the yth column of the decision matrix, , , …, are the components of vector E, is the information entropy of the yth column of the standardized decision matrix, E is the entropy vector, is the normalized information entropy weight of the yth column of the standardized decision matrix, is the weighted decision matrix, is the value of the 1st, 2nd, …, mth columns of the standardized decision matrix, is the normalized information entropy weight of the 1st, 2nd, …, mth columns of the standardized decision matrix, The value of the positive ideal solution in the yth column of the weighted decision matrix, is the value of the negative ideal solution in the yth column of the weighted decision matrix, , and are the values ​​of the 1st, 2nd and 3rd rows of the weighted decision matrix, is the value of the xth row and yth column of the weighted decision matrix, is the distance to the positive ideal solution in the xth row of the weighted decision matrix, is the distance to the negative ideal solution of the x-th row of the weighted decision matrix, is the feature weight of the x-th row of the decision matrix, m is the number of decision matrix columns, x≤3, y≤m, and x, y and m are all positive integers, max is the maximum value function, and min is the minimum value function.

7. The method for cleaning foreign matter from a coal conveyor belt based on visual characteristics according to claim 6 is characterized in that: Determining a comprehensive descriptor of foreign matter on the surface of the coal conveyor belt according to the original image feature, the Gram angle and field feature, the Gram angle difference field feature, the original image feature weight, the Gram angle and field feature weight, and the Gram angle difference field feature weight includes: According to the formula A comprehensive descriptor F for determining foreign matter on the surface of coal conveyor belts.

8. A visual feature coal conveyor belt foreign body cleaning system, used to perform the visual feature coal conveyor belt foreign body cleaning method as described in any one of claims 1 to 7, characterized in that: include: The original image module is used to obtain the original image of the coal conveyor belt by installing a camera; A Gram angle sum field image and a Gram angle difference field image module, used for analyzing and processing the original image to determine a Gram angle sum field image and a Gram angle difference field image; A comprehensive descriptor module, for determining a comprehensive descriptor of foreign matter on the surface of the coal conveyor belt according to the original image, the Gram angle sum field image and the Gram angle difference field image; A foreign body identification result module, used for inputting the comprehensive descriptor into a classifier to obtain a foreign body identification result; A judgment module, used to determine whether to start a cleaning device for cleaning according to the foreign object recognition result; The feedback module is used to feedback the cleaning effect after the cleaning device is started to clean until there is no foreign matter on the belt surface.

Images