Method, device, electronic device and readable storage medium for measuring ore and rock block size

Abstract

The present application provides a method, device, electronic device and readable storage medium for measuring the block size of mineral rocks. Applied to the technical field of block size measurement of mineral rocks, the method includes calculating the gradient value and the standard deviation value of the gradient difference corresponding to any pixel in the grayscale image; if the corresponding pixel is a candidate edge pixel, the corresponding several associated pixels on the candidate edge fusion map are voted; according to the number of votes, it is judged whether the corresponding pixel is a candidate edge fusion pixel to obtain a mineral rock segmentation map; according to the internal parameter calibration matrix and the external parameter calibration matrix, the point cloud image mapping relationship is obtained; according to the point cloud image mapping relationship, the three-dimensional point cloud of the mineral rock collected by the laser radar and the mineral rock segmentation map are mapped, plane fitted and projected to the fitting plane, and sparsity screening is performed to obtain a high-density target rock block point cloud; the calibration coefficient and the corresponding rock block block size are calculated. In this way, the accuracy of mineral rock block size calculation can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of ore rock blockiness measurement, and in particular to a ore rock blockiness measurement method, device, electronic equipment and readable storage medium. Background Art

[0002] In the blasting mining process of mines, the quality of blasting directly determines the size distribution of ore rocks. If the size is too large, the ore may not be able to pass through the crushing equipment smoothly, thus affecting the subsequent transportation and processing efficiency. If the size is too small, although it is conducive to crushing and transportation, it may increase unnecessary energy consumption and reduce economic benefits. Through the measurement of ore rock size, the blasting design can be optimized, the size distribution of ore rocks can be controlled, thereby improving the production efficiency of mines; in mining production, ore crushing and grinding are indispensable links. The size of ore rock size directly affects the selection and operation efficiency of crushing and grinding equipment. Ore with too large a size may require longer time or higher energy consumption to crush, while ore with too small a size may cause increased equipment wear and reduce the service life of the equipment. Through the measurement of ore rock size, the parameters of the crushing equipment can be reasonably adjusted, the crushing process can be optimized, energy consumption can be reduced, and the life of the equipment can be extended, thereby improving the overall economic benefits of production; overly large ore rock blocks may roll or collapse during transportation, causing equipment Damage and even casualties. In underground mines, oversized ore blocks may cause blockage of tunnels, affect ventilation and drainage, and increase the risk of mine accidents. By measuring and monitoring the block size of ore blocks, mining and blasting plans can be adjusted in time to reduce safety hazards and ensure safe production in mines. Oversized ore blocks may cause difficulties in stacking during tailings treatment and increase the risk of environmental pollution, while undersized blocks may cause the loss of fine-grained minerals in tailings, resulting in waste of resources. By measuring the block size of ore blocks, tailings treatment processes can be optimized to reduce the impact on the environment, while improving the recovery rate of resources and realizing the comprehensive utilization of resources. By optimizing blasting design and crushing technology, mines can reduce unnecessary energy consumption and equipment wear, and reduce production costs. At the same time, reasonable block size distribution can improve the processing efficiency of ore and increase the recovery rate of ore, thereby improving the overall economic benefits of mines. Reasonable control of ore block size can also reduce ore waste, improve the comprehensive utilization rate of resources, and further increase the economic benefits of mines. Therefore, it is of great significance to measure the block size of ore blocks.

[0003] At present, in the process of measuring the block size of mineral rocks, the block size calculation methods based on image modality and the block size calculation methods based on three-dimensional point cloud modality are usually used. The former is because the mineral rock image only has color and texture information but no spatial information and geometric position information. Therefore, it is impossible to directly calculate the block size of mineral rocks accurately under image modality. The latter is because the point cloud resolution obtained by the vehicle-mounted laser radar is usually lower than the image, the morphology of some rock blocks cannot be fully described by point cloud, and there is a lack of fine-grained information, so the mineral rock blocks cannot be accurately segmented, resulting in low accuracy in the calculation of mineral rock block size. Summary of the invention

[0004] The present disclosure provides a method, device, electronic device and readable storage medium for measuring the blockiness of minerals and rocks.

[0005] According to a first aspect of the present disclosure, a method for measuring the size of mineral rocks is provided. The method comprises:

[0006] Obtain a color image of the ore rock taken by a camera, and convert the color image into a grayscale image; based on the grayscale image, calculate the gradient value corresponding to any pixel in the grayscale image; based on the gradient value, calculate the standard deviation value of the gradient difference of the corresponding pixel;

[0007] Create a candidate edge fusion map; determine whether the corresponding pixel is a candidate edge pixel according to the gradient value and the gradient difference standard deviation value corresponding to any pixel in the grayscale image; if so, the corresponding several associated pixels on the candidate edge fusion map are voted, and at the same time, several adjacent pixels of the associated pixel in the direction perpendicular to the gradient are also voted; determine whether the corresponding pixel is a candidate edge fusion pixel according to the number of votes for any pixel in the candidate edge fusion map; obtain an intermediate edge fusion map according to each of the candidate edge fusion pixels and the candidate edge fusion map; perform a lag connection on the intermediate edge fusion map to obtain a final edge fusion map; process the final edge fusion map by a watershed algorithm to obtain a mineral rock segmentation map;

[0008] Performing internal parameter calibration on the camera to obtain an internal parameter calibration matrix; performing joint calibration on the camera and the laser radar to obtain an external parameter calibration matrix; obtaining a point cloud image mapping relationship according to the internal parameter calibration matrix and the external parameter calibration matrix; mapping the three-dimensional point cloud of the ore rock collected by the laser radar and the ore rock segmentation map according to the point cloud image mapping relationship to obtain a ore rock block segmentation point cloud; performing plane fitting on the ore rock block segmentation point cloud and projecting it onto the fitting plane to obtain a ore rock block segmentation plane point cloud; performing sparsity screening on each rock block in the ore rock block segmentation plane point cloud to obtain a high-density target rock block point cloud;

[0009] In the ore rock block segmentation plane point cloud, a first minimum circumscribed rectangle is drawn for the high-density target rock block point cloud to obtain a first rectangle length and a first rectangle width; in the ore rock segmentation map, a second minimum circumscribed rectangle is drawn for the rock block image corresponding to the high-density target rock block point cloud to obtain a second rectangle length and a second rectangle width; a calibration coefficient is calculated based on the first rectangle length, the first rectangle width, the second rectangle length and the second rectangle width; the blockiness of the corresponding rock block is calculated based on the calibration coefficient and the number of pixels corresponding to each rock block in the ore rock segmentation map.

[0010] Furthermore, the calculation formula of the standard deviation of the gradient difference of the corresponding pixel is:

[0011]

[0012]

[0013]

[0014] in, Pixel With local neighborhood The gradient difference of any pixel in is the gradient value of pixel (i+m,j+n); Pixel The gradient value of Pixel With local neighborhood The mean of the gradient differences of all pixels in ; Pixel With local neighborhood The standard deviation of the gradient difference of all pixels in the pixel The standard deviation of the gradient.

[0015] Furthermore, judging whether a corresponding pixel is a candidate edge pixel according to the gradient value and the gradient difference standard deviation value corresponding to any pixel in the grayscale image includes:

[0016] Calculating a mean value of the gradient corresponding to each pixel in the grayscale image according to the gradient value corresponding to each pixel in the grayscale image;

[0017] Calculating the mean value of the gradient difference standard deviation corresponding to the grayscale image according to the gradient difference standard deviation value corresponding to each pixel in the grayscale image;

[0018] If the gradient value corresponding to any pixel in the grayscale image is ≥ the mean value of the gradient value, and the standard deviation value of the gradient difference of the corresponding pixel is ≥ the mean value of the standard deviation value of the gradient difference, then the corresponding pixel is judged to be a candidate edge pixel, and the grayscale value of the corresponding pixel is set to the sum of the corresponding gradient value and the corresponding standard deviation value of the gradient difference; wherein the range of the corresponding gradient value and the corresponding standard deviation value of the gradient difference are both [0,255];

[0019] If the gradient value corresponding to any pixel in the grayscale image is less than the gradient value mean, or the gradient difference standard deviation value of the corresponding pixel is less than the gradient difference standard deviation value mean, the corresponding pixel is judged to be a noise point, and the grayscale value of the corresponding pixel is set to 0.

[0020] Furthermore, if so, a number of corresponding associated pixels on the candidate edge fusion map are voted, and at the same time, a number of adjacent pixels of the associated pixels in a direction perpendicular to the gradient are also voted; according to the number of votes for any pixel in the candidate edge fusion map, determining whether the corresponding pixel is a candidate edge fusion pixel includes:

[0021] According to the grayscale image, a multi-scale image pyramid is created to obtain a first scale-level grayscale image, a second scale-level grayscale image, ..., an Lth scale-level grayscale image, ..., an Lth scale-level grayscale image, ..., an Lth scale-level grayscale image m Scale level grayscale image; L m represents the maximum scale level of the multi-scale image pyramid;

[0022] If any pixel (a, b) in the Lth scale level grayscale image is a candidate edge pixel, then the corresponding associated pixel (a×2 L ,b×2 L ) is voted, and at the same time, the associated pixel (a×2 L ,b×2 L ) The L neighboring pixels perpendicular to the gradient direction are also voted;

[0023] The number of votes for any pixel on the candidate edge fusion map To conduct statistics;

[0024] like ,in represents a round-up operation, the corresponding pixel on the candidate edge fusion image is the candidate edge fusion pixel, and the grayscale value of the corresponding pixel is set to the sum of the gradient value of the corresponding pixel in the grayscale image and the standard deviation value of the gradient difference.

[0025] Furthermore, the joint calibration of the camera and the laser radar includes:

[0026] Using a 3D laser radar in a multimodal 3D environment perception system to collect multiple sets of 3D laser point clouds containing black and white checkerboard calibration plates in different postures; using a camera in the multimodal 3D environment perception system to collect multiple sets of 2D images containing black and white checkerboard calibration plates in different postures; wherein each set of 3D laser point clouds and 2D images are collected at the same sampling time;

[0027] Using multiple sets of two-dimensional images containing a checkerboard calibration plate in different poses, the camera intrinsic parameter matrix is ​​calculated based on Zhang Zhengyou's calibration method. At the same time, through the intrinsic parameter calibration, the pose relationship between the calibration plate coordinate system and the camera coordinate system in different poses is calculated;

[0028] Using the external parameter calibration method of 3D laser radar and camera, the linear equations of line-surface geometric constraints and surface-surface geometric constraints are jointly constructed, and the initial external parameter matrix is ​​solved using the least squares method;

[0029] A global error consisting of the pixel projection error caused by the camera intrinsic calibration and the laser point vertical distance error caused by the initial extrinsic calibration is constructed. The Levenberg-Marquardt method is used for nonlinear global optimization solution to complete the final extrinsic calibration.

[0030] Furthermore, the calculation formula of the calibration coefficient is:

[0031]

[0032] in, is the length of the first rectangle; is the width of the first rectangle; is the length of the second rectangle; is the width of the second rectangle; is the calibration coefficient; The unit is cm / pixel.

[0033] Furthermore, the block size calculation formula of the rock block in the ore rock segmentation diagram is:

[0034]

[0035] in, The number of pixels in the ore rock segmentation map is The size of the rock mass; is the calibration factor.

[0036] According to a second aspect of the present disclosure, a device for measuring the size of mineral rocks is provided. The device comprises:

[0037] The first calculation module is used to obtain a color image of the ore rock taken by a camera, and convert the color image into a grayscale image; based on the grayscale image, calculate the gradient value corresponding to any pixel in the grayscale image; based on the gradient value, calculate the standard deviation value of the gradient difference of the corresponding pixel;

[0038] The first determination module is used to create a candidate edge fusion map; according to the gradient value and the gradient difference standard deviation value corresponding to any pixel in the grayscale image, determine whether the corresponding pixel is a candidate edge pixel; if so, then the corresponding several associated pixels on the candidate edge fusion map are voted, and at the same time, several adjacent pixels of the associated pixel in the direction perpendicular to the gradient are also voted; according to the number of votes of any pixel in the candidate edge fusion map, determine whether the corresponding pixel is a candidate edge fusion pixel; according to each of the candidate edge fusion pixels and the candidate edge fusion map, obtain an intermediate edge fusion map; perform lag connection on the intermediate edge fusion map to obtain a final edge fusion map; process the final edge fusion map by a watershed algorithm to obtain a mineral rock segmentation map;

[0039] The second determination module is used to perform internal parameter calibration on the camera to obtain an internal parameter calibration matrix; perform joint calibration on the camera and the laser radar to obtain an external parameter calibration matrix; obtain a point cloud image mapping relationship according to the internal parameter calibration matrix and the external parameter calibration matrix; map the three-dimensional point cloud of the ore rock collected by the laser radar and the ore rock segmentation map according to the point cloud image mapping relationship to obtain a ore rock block segmentation point cloud; perform plane fitting on the ore rock block segmentation point cloud and project it to the fitting plane to obtain a ore rock block segmentation plane point cloud; perform sparsity screening on each rock block in the ore rock block segmentation plane point cloud to obtain a high-density target rock block point cloud;

[0040] The second calculation module is used to draw a first minimum circumscribed rectangle for the high-density target rock block point cloud in the mineral rock block segmentation plane point cloud to obtain a first rectangle length and a first rectangle width; in the mineral rock segmentation map, draw a second minimum circumscribed rectangle for the rock block image corresponding to the high-density target rock block point cloud to obtain a second rectangle length and a second rectangle width; calculate a calibration coefficient based on the first rectangle length, the first rectangle width, the second rectangle length and the second rectangle width; calculate the blockiness of the corresponding rock block based on the calibration coefficient and the number of pixels corresponding to each rock block in the mineral rock segmentation map.

[0041] According to a third aspect of the present disclosure, an electronic device is provided. The electronic device includes: a memory and a processor, wherein a computer program is stored in the memory, and the method is implemented when the processor executes the program.

[0042] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and the program implements the method when executed by a processor.

[0043] The present invention obtains a color image of the mineral rock and converts it into a grayscale image, and then performs edge detection based on the gradient value and the standard deviation value of the gradient difference, so as to accurately extract the surface edge of the mineral rock, reduce the error caused by noise or illumination change in the traditional image processing method, improve the accuracy of edge detection, and provide a more accurate basis for the subsequent mineral rock segmentation; by combining the internal and external parameter calibration of the camera with the point cloud information of the laser radar, the three-dimensional data and the two-dimensional segmentation map are integrated by using the point cloud image mapping relationship, which not only improves the accuracy of mineral rock segmentation, but also enhances the adaptability of the model to complex mineral rock morphology, and can effectively reduce the probability of misjudgment; by performing plane fitting on the mineral rock segmentation point cloud and performing sparse screening in the high-density area, the geometric features of the mineral rock block can be accurately identified and extracted, and the calculation of the minimum circumscribed rectangle further improves the accuracy of the block size measurement, so that the measurement result can better reflect the true size of the mineral rock block; and it can achieve high-accuracy mineral rock block size calculation without relying on external markers.

[0044] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0046] Figure 1 A flow chart of a method for measuring the size of mineral rocks according to an embodiment of the present disclosure is shown;

[0047] Figure 2 A block diagram of a device for measuring the size of mineral rocks according to an embodiment of the present disclosure is shown;

[0048] Figure 3 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0050] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0051] Figure 1 A flow chart of a method 100 for measuring the size of a mineral rock according to an embodiment of the present disclosure is shown. The method 100 comprises:

[0052] S101, obtaining a color image of the ore rock taken by a camera, and converting the color image into a grayscale image; calculating a gradient value corresponding to any pixel in the grayscale image according to the grayscale image; and calculating a gradient difference standard deviation value of the corresponding pixel according to the gradient value;

[0053] According to the embodiment of the present invention, by converting a color image into a grayscale image, the complexity of subsequent calculations is reduced and the operation efficiency is improved.

[0054] In some embodiments, after the color image is converted into a grayscale image, a median filter is performed on the grayscale image, and the calculation formula may be:

[0055]

[0056] in, is the gray value of pixel (i, j) after median filtering, is the gray value of pixel (ia, jb) before median filtering, According to the embodiment of the present invention, by performing median filtering on the grayscale image, it is helpful to smooth the surface texture of the ore and filter out isolated noise points, thereby improving the accuracy of ore block size calculation.

[0057] In some embodiments, according to the grayscale image, the calculation formula of the gradient value corresponding to any pixel in the grayscale image may be:

[0058]

[0059]

[0060]

[0061]

[0062]

[0063]

[0064] in, is the convolution template in the x direction, is the convolution template in the y direction, is the gradient value of pixel (i, j) in the x direction, is the gradient value of pixel (i, j) in the y direction, Represents the convolution operation, G(i,j) is the gradient value of pixel (i,j), and θ(i,j) is the gradient direction of pixel (i,j).

[0065] In some embodiments, the calculation formula of the standard deviation value of the gradient difference of the corresponding pixel can be:

[0066]

[0067]

[0068]

[0069] in, Pixel With local neighborhood The gradient difference of any pixel in is the gradient value of pixel (i+m,j+n); Pixel The gradient value of Pixel With local neighborhood The mean of the gradient differences of all pixels in ; Pixel With local neighborhood The standard deviation of the gradient difference of all pixels in the pixel According to an embodiment of the present invention, by calculating the standard deviation of the gradient difference for subsequent operations, it is avoided that the direct use of the gradient value cannot effectively distinguish edge points and noise points, resulting in low accuracy of mineral rock block segmentation caused by over-segmentation or under-segmentation of the image, thereby improving the accuracy of mineral rock block calculation.

[0070] S102, creating a candidate edge fusion map; judging whether the corresponding pixel is a candidate edge pixel according to the gradient value and the standard deviation value of the gradient difference corresponding to any pixel in the grayscale image; if so, the corresponding several associated pixels on the candidate edge fusion map are voted, and at the same time, several adjacent pixels of the associated pixel in the direction perpendicular to the gradient are also voted; judging whether the corresponding pixel is a candidate edge fusion pixel according to the number of votes of any pixel in the candidate edge fusion map; obtaining an intermediate edge fusion map according to each of the candidate edge fusion pixels and the candidate edge fusion map; performing a lag connection on the intermediate edge fusion map to obtain a final edge fusion map; processing the final edge fusion map by a watershed algorithm to obtain a mineral rock segmentation map;

[0071] In some embodiments, judging whether a corresponding pixel is a candidate edge pixel according to a gradient value and a gradient difference standard deviation value corresponding to any pixel in the grayscale image includes:

[0072] According to the gradient values ​​corresponding to each pixel in the grayscale image, the mean gradient value corresponding to the grayscale image is calculated; for example, the calculation formula of the mean gradient value may be:

[0073]

[0074] in, is the mean gradient value corresponding to the grayscale image, is the width of the grayscale image, is the length dimension, For grayscale images, the pixel The gradient value at ;

[0075] According to the standard deviation of the gradient difference corresponding to each pixel in the grayscale image, the mean of the standard deviation of the gradient difference corresponding to the grayscale image is calculated; for example, the calculation formula of the mean of the standard deviation of the gradient difference can be:

[0076]

[0077] in, is the mean value of the standard deviation of the gradient difference corresponding to the grayscale image, is the width of the grayscale image, is the length dimension, For grayscale images, the pixel The standard deviation of the gradient difference at ;

[0078] If the gradient value corresponding to any pixel in the grayscale image is ≥ the mean value of the gradient value, and the standard deviation value of the gradient difference of the corresponding pixel is ≥ the mean value of the standard deviation value of the gradient difference, then the corresponding pixel is judged to be a candidate edge pixel, and the grayscale value of the corresponding pixel is set to the sum of the corresponding gradient value and the corresponding standard deviation value of the gradient difference; wherein the range of the corresponding gradient value and the corresponding standard deviation value of the gradient difference are both [0,255];

[0079] If the gradient value corresponding to any pixel in the grayscale image is less than the gradient value mean, or the gradient difference standard deviation value of the corresponding pixel is less than the gradient difference standard deviation value mean, the corresponding pixel is judged to be a noise point, and the grayscale value of the corresponding pixel is set to 0.

[0080] According to an embodiment of the present invention, by calculating the mean of the gradient value and the mean of the gradient difference standard deviation, the edge pixels in the image can be more accurately identified. The gradient value indicates the degree of change in pixel intensity, and the gradient difference standard deviation describes the distribution of gradient changes around the pixel. When the gradient value is high and the gradient difference standard deviation is large, it indicates that there is significant edge information in the image. The statistical information of the gradient value and the gradient change is combined to improve the accuracy of edge detection. When the gradient value of a pixel is lower than the mean, or the gradient difference standard deviation is low, it indicates that the pixel is a noise point. By setting the grayscale value of these noise points to 0, the noise in the image can be effectively removed and the influence of noise on the edge detection result can be reduced. This noise suppression is based on local statistical features and can improve the effect of noise filtering. The introduction of the gradient difference standard deviation enables the scheme to consider not only the local changes of each pixel, but also the degree of change in the local area, so that the edge can be detected more stably, especially in areas with complex textures or more noise, it can reduce misjudgment, more effectively identify the real edge, and improve the accuracy of mineral rock block calculation, which helps to achieve high-accuracy mineral rock block calculation without relying on external markers.

[0081] In some embodiments, a non-maximum suppression method is used to refine the candidate edge to ensure that the edge is a single pixel width. By comparing the candidate edge pixel (i, j) with its adjacent pixels along the gradient direction, it is determined whether its grayscale value is a local maximum; if so, its grayscale value remains unchanged; if not, its grayscale value is set to 0 in the candidate edge map. According to an embodiment of the present invention, through non-maximum suppression, only those pixels that are indeed local maxima in the gradient direction will be retained, thereby avoiding the interference of non-edge pixels, ensuring the authenticity and accuracy of the edge, and reducing the situation of false detection; non-maximum suppression can remove potential noise and irrelevant details by eliminating pixels that are not local maxima, thereby ensuring that only significant edge features are retained in the edge map, reducing the impact of noise on the final detection result; by refining the edge, the detected edge position is made more accurate, especially when processing some subtle edges or high-contrast edges, non-maximum suppression can effectively avoid the "edge blur" phenomenon and ensure the accurate positioning of the edge.

[0082] In some embodiments, if so, a number of corresponding associated pixels on the candidate edge fusion map are voted, and at the same time, a number of adjacent pixels of the associated pixel in a direction perpendicular to the gradient are also voted; according to the number of votes for any pixel in the candidate edge fusion map, determining whether the corresponding pixel is a candidate edge fusion pixel includes:

[0083] According to the grayscale image, a multi-scale image pyramid is created to obtain a first scale-level grayscale image, a second scale-level grayscale image, ..., an Lth scale-level grayscale image, ..., an Lth scale-level grayscale image, ..., an Lth scale-level grayscale image m Scale level grayscale image; L m represents the maximum scale level of the multi-scale image pyramid;

[0084] If any pixel (a, b) in the Lth scale level grayscale image is a candidate edge pixel, then the corresponding associated pixel (a×2 L ,b×2 L ) is voted, and at the same time, the associated pixel (a×2 L ,b×2 L ) The L neighboring pixels perpendicular to the gradient direction are also voted;

[0085] The number of votes for any pixel on the candidate edge fusion map To conduct statistics;

[0086] like ,in represents a round-up operation, the corresponding pixel on the candidate edge fusion image is the candidate edge fusion pixel, and the grayscale value of the corresponding pixel is set to the sum of the gradient value of the corresponding pixel in the grayscale image and the standard deviation value of the gradient difference.

[0087] In some embodiments, the intermediate edge fusion map is connected with a lag connection to obtain a final edge fusion map, including: creating a feature fusion map; the grayscale value calculation formula of any pixel in the feature fusion map is:

[0088]

[0089] Among them, F(i,j) is the gray value of the pixel (i,j) of the feature fusion image, is the gradient value of pixel (i, j) on the original scale image, is the standard deviation of the local gradient difference of pixel (i, j) in the original scale image;

[0090] The high threshold of the feature fusion map is calculated using the Otsu method , high threshold The calculation is as follows:

[0091]

[0092] in, On behalf of Otsufa, is the adjustment factor, the default value is 0.8;

[0093] Use high threshold Perform thresholding on the feature fusion map;

[0094] Create the remaining feature map. The grayscale value of the pixel (i, j) in the remaining feature map is calculated as follows:

[0095]

[0096] Based on the remaining feature maps, calculate the low threshold Specifically, since the obvious strong edges have been removed, the remaining edges in the remaining feature map are relatively blurred. Since the Otsu method has a poor processing effect on blurred edges, it is easy to cause edge pixel loss. The maximum entropy threshold method based on information entropy theory has a better effect on processing blurred edges. Therefore, the maximum entropy threshold method is used to calculate the low threshold in the remaining feature map. ,The 2D maximum entropy threshold method uses information entropy theory to calculate the optimal threshold, which maximizes the sum of the information entropy of the target and the background, taking into account both the grayscale distribution information of the pixels and the spatial correlation information between the pixels. The calculation is as follows: ,in, represents the maximum entropy threshold method;

[0097] Based on high threshold and low threshold The intermediate edge fusion image is connected laggingly to obtain the final edge fusion image, as follows: If the gray value of any pixel in the intermediate edge fusion image is > , the corresponding pixel in the final edge fusion image is determined as an edge pixel, and the grayscale value is set to 255; if the grayscale value of any pixel in the intermediate edge fusion image is less than , then the corresponding pixel in the final edge fusion image is judged as a non-edge pixel, and the gray value is set to 0; if ≤The gray value of any pixel in the middle edge fusion image≤ , it is further verified whether there is an edge pixel in the local neighborhood of the corresponding pixel of the final edge fusion image. If so, the corresponding pixel of the final edge fusion image is determined to be an edge pixel, and the grayscale value is set to 255; if not, the corresponding pixel of the final edge fusion image is determined to be a non-edge pixel, and the grayscale value is set to 0.

[0098] In some embodiments, based on the final edge fusion map E, the standard deviation map The pixels corresponding to the edge pixels are enhanced to increase the difference between the watershed and the catchment basin, effectively avoiding submerging important edges and reducing the occurrence of under-segmentation. Specifically, if the grayscale value and standard deviation map of the pixels on the final edge fusion map E The grayscale values ​​of the corresponding pixels on satisfy the following conditions: in, Standard deviation graph The median of all pixel values ​​on the graph, then let the standard deviation map The grayscale value of the pixel (i, j) is: ; If the conditions are not met, then in the standard deviation graph Keep the original pixel value unchanged.

[0099] S103, perform internal parameter calibration on the camera to obtain an internal parameter calibration matrix; perform joint calibration on the camera and the laser radar to obtain an external parameter calibration matrix; obtain a point cloud image mapping relationship according to the internal parameter calibration matrix and the external parameter calibration matrix; map the three-dimensional point cloud of the ore rock collected by the laser radar and the ore rock segmentation map according to the point cloud image mapping relationship to obtain a ore rock block segmentation point cloud; perform plane fitting on the ore rock block segmentation point cloud and project it onto the fitting plane to obtain a ore rock block segmentation plane point cloud; perform sparsity screening on each rock block in the ore rock block segmentation plane point cloud to obtain a high-density target rock block point cloud;

[0100] In some embodiments, the camera is calibrated intrinsically based on a checkerboard calibration plate to obtain a camera intrinsic calibration matrix. , and jointly calibrate the camera and lidar to obtain the external parameter calibration matrix Assumptions represents any point in the laser coordinate system, Indicates the mapping pixel of the point in the image coordinate system; point and mapped pixels The homogeneous coordinates of are expressed as and ; Based on the pinhole imaging model, it can be calculated and The mapping relationship between them is: , which one, is an arbitrary scaling factor.

[0101] In some embodiments, the joint calibration of the camera and the laser radar includes: using the three-dimensional laser radar in the multimodal three-dimensional environment perception system to collect multiple groups of three-dimensional laser point clouds containing black and white checkerboard calibration plates in different postures; using the camera in the multimodal three-dimensional environment perception system to collect multiple groups of two-dimensional images containing black and white checkerboard calibration plates in different postures; wherein each group of three-dimensional laser point clouds and two-dimensional images are collected at the same sampling time; using multiple groups of two-dimensional images containing checkerboard calibration plates in different postures, the camera intrinsic parameter matrix is ​​calculated based on the Zhang Zhengyou calibration method, and at the same time, through the intrinsic parameter calibration, the posture relationship between the calibration plate coordinate system and the camera coordinate system in different postures is calculated; using the external parameter calibration method of the three-dimensional laser radar and the camera, a linear equation group of line-surface geometric constraints and surface-surface geometric constraints is jointly constructed, and the initial external parameter matrix is ​​solved by the least squares method; a global error composed of the pixel projection error caused by the camera intrinsic parameter calibration and the laser point vertical distance error caused by the initial external parameter calibration is constructed, and the Levenberg-Marquardt method is used for nonlinear global optimization solution to complete the final external parameter calibration.

[0102] S104, in the ore rock block segmentation plane point cloud, draw a first minimum circumscribed rectangle for the high-density target rock block point cloud to obtain a first rectangle length and a first rectangle width; in the ore rock segmentation map, draw a second minimum circumscribed rectangle for the rock block image corresponding to the high-density target rock block point cloud to obtain a second rectangle length and a second rectangle width; calculate a calibration coefficient based on the first rectangle length, the first rectangle width, the second rectangle length and the second rectangle width; calculate the blockiness of the corresponding rock block based on the calibration coefficient and the number of pixels corresponding to each rock block in the ore rock segmentation map.

[0103] In some embodiments, the calculation formula of the calibration coefficient is:

[0104]

[0105] in, is the length of the first rectangle; is the width of the first rectangle; is the length of the second rectangle; is the width of the second rectangle; is the calibration coefficient; The unit is cm / pixel.

[0106] In some embodiments, the block size calculation formula of the rock block in the ore rock segmentation diagram is:

[0107]

[0108] in, The number of pixels in the ore rock segmentation map is The size of the rock mass; is the calibration factor.

[0109] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0110] The above is an introduction to the method embodiment. The following is a further explanation of the scheme disclosed in the present invention through an apparatus embodiment.

[0111] Figure 2 A block diagram of a device for measuring the size of mineral rocks according to an embodiment of the present disclosure is shown, the device comprising:

[0112] The first calculation module is used to obtain a color image of the ore rock taken by a camera, and convert the color image into a grayscale image; based on the grayscale image, calculate the gradient value corresponding to any pixel in the grayscale image; based on the gradient value, calculate the standard deviation value of the gradient difference of the corresponding pixel;

[0113] The first determination module is used to create a candidate edge fusion map; according to the gradient value and the gradient difference standard deviation value corresponding to any pixel in the grayscale image, determine whether the corresponding pixel is a candidate edge pixel; if so, then the corresponding several associated pixels on the candidate edge fusion map are voted, and at the same time, several adjacent pixels of the associated pixel in the direction perpendicular to the gradient are also voted; according to the number of votes of any pixel in the candidate edge fusion map, determine whether the corresponding pixel is a candidate edge fusion pixel; according to each of the candidate edge fusion pixels and the candidate edge fusion map, obtain an intermediate edge fusion map; perform lag connection on the intermediate edge fusion map to obtain a final edge fusion map; process the final edge fusion map by a watershed algorithm to obtain a mineral rock segmentation map;

[0114] The second determination module is used to perform internal parameter calibration on the camera to obtain an internal parameter calibration matrix; perform joint calibration on the camera and the laser radar to obtain an external parameter calibration matrix; obtain a point cloud image mapping relationship according to the internal parameter calibration matrix and the external parameter calibration matrix; map the three-dimensional point cloud of the ore rock collected by the laser radar and the ore rock segmentation map according to the point cloud image mapping relationship to obtain a ore rock block segmentation point cloud; perform plane fitting on the ore rock block segmentation point cloud and project it to the fitting plane to obtain a ore rock block segmentation plane point cloud; perform sparsity screening on each rock block in the ore rock block segmentation plane point cloud to obtain a high-density target rock block point cloud;

[0115] The second calculation module is used to draw a first minimum circumscribed rectangle for the high-density target rock block point cloud in the mineral rock block segmentation plane point cloud to obtain a first rectangle length and a first rectangle width; in the mineral rock segmentation map, draw a second minimum circumscribed rectangle for the rock block image corresponding to the high-density target rock block point cloud to obtain a second rectangle length and a second rectangle width; calculate a calibration coefficient based on the first rectangle length, the first rectangle width, the second rectangle length and the second rectangle width; calculate the blockiness of the corresponding rock block based on the calibration coefficient and the number of pixels corresponding to each rock block in the mineral rock segmentation map.

[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0117] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0118] Figure 3A schematic block diagram of an electronic device that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0119] The electronic device includes a computing unit, which can perform various appropriate actions and processes according to a computer program stored in a ROM or a computer program loaded from a storage unit into a RAM. In the RAM, various programs and data required for the operation of the electronic device can also be stored. The computing unit, ROM, and RAM are connected to each other via a bus. An I / O interface is also connected to the bus.

[0120] Multiple components in an electronic device are connected to the I / O interface, including: input units, such as keyboards, mice, etc.; output units, such as various types of displays, speakers, etc.; storage units, such as disks, optical disks, etc.; and communication units, such as network cards, modems, wireless communication transceivers, etc. The communication unit allows the electronic device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunication networks.

[0121] The computing unit may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of computing units include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit performs the various methods and processes described above, such as the ore rock block size measurement method. For example, in some embodiments, the ore rock block size measurement method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on an electronic device via a ROM and / or a communication unit. When the computer program is loaded into RAM and executed by the computing unit, one or more steps of the ore rock block size measurement method described above may be performed. Alternatively, in other embodiments, the computing unit may be configured to perform the ore rock block size measurement method in any other appropriate manner (e.g., by means of firmware).

[0122] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0123] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0124] In the context of the present disclosure, a readable storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A readable storage medium may be a machine-readable signal medium or a machine-readable storage medium. A readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of readable storage media may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0125] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0126] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0127] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0128] It should be understood that the above-mentioned various forms of processes can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution of this disclosure can be achieved, and this document does not limit this.

[0129] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for measuring the blockiness of minerals and rocks, characterized in that: include: Obtaining a color image of the ore rock taken by a camera, and converting the color image into a grayscale image; According to the grayscale image, a gradient value corresponding to any pixel in the grayscale image is calculated; According to the gradient value, a standard deviation value of the gradient difference of the corresponding pixel is calculated; Create a candidate edge fusion map; determine whether the corresponding pixel is a candidate edge pixel according to the gradient value and the gradient difference standard deviation value corresponding to any pixel in the grayscale image; if so, the corresponding several associated pixels on the candidate edge fusion map are voted, and at the same time, several adjacent pixels of the associated pixel in the direction perpendicular to the gradient are also voted; determine whether the corresponding pixel is a candidate edge fusion pixel according to the number of votes for any pixel in the candidate edge fusion map; obtain an intermediate edge fusion map according to each of the candidate edge fusion pixels and the candidate edge fusion map; perform a lag connection on the intermediate edge fusion map to obtain a final edge fusion map; process the final edge fusion map by a watershed algorithm to obtain a mineral rock segmentation map; Performing internal parameter calibration on the camera to obtain an internal parameter calibration matrix; performing joint calibration on the camera and the laser radar to obtain an external parameter calibration matrix; obtaining a point cloud image mapping relationship according to the internal parameter calibration matrix and the external parameter calibration matrix; mapping the three-dimensional point cloud of the ore rock collected by the laser radar and the ore rock segmentation map according to the point cloud image mapping relationship to obtain a ore rock block segmentation point cloud; performing plane fitting on the ore rock block segmentation point cloud and projecting it onto the fitting plane to obtain a ore rock block segmentation plane point cloud; performing sparsity screening on each rock block in the ore rock block segmentation plane point cloud to obtain a high-density target rock block point cloud; In the ore rock block segmentation plane point cloud, a first minimum circumscribed rectangle is drawn for the high-density target rock block point cloud to obtain a first rectangle length and a first rectangle width; in the ore rock segmentation map, a second minimum circumscribed rectangle is drawn for the rock block image corresponding to the high-density target rock block point cloud to obtain a second rectangle length and a second rectangle width; a calibration coefficient is calculated based on the first rectangle length, the first rectangle width, the second rectangle length and the second rectangle width; the blockiness of the corresponding rock block is calculated based on the calibration coefficient and the number of pixels corresponding to each rock block in the ore rock segmentation map.

2. The method for measuring the size of mineral rocks according to claim 1, characterized in that: The calculation formula of the gradient difference standard deviation value of the corresponding pixel is: ； ； ； in, Pixel With local neighborhood The gradient difference of any pixel in is the gradient value of pixel (i+m,j+n); Pixel The gradient value of Pixel With local neighborhood The mean of the gradient differences of all pixels in ; Pixel With local neighborhood The standard deviation of the gradient difference of all pixels in the pixel The standard deviation of the gradient.

3. The method for measuring the size of mineral rocks according to claim 2, characterized in that: The step of judging whether a corresponding pixel is a candidate edge pixel according to the gradient value and the gradient difference standard deviation value corresponding to any pixel in the grayscale image includes: Calculating a mean value of the gradient corresponding to each pixel in the grayscale image according to the gradient value corresponding to each pixel in the grayscale image; Calculating the mean value of the gradient difference standard deviation corresponding to the grayscale image according to the gradient difference standard deviation value corresponding to each pixel in the grayscale image; If the gradient value corresponding to any pixel in the grayscale image is ≥ the mean value of the gradient value, and the standard deviation value of the gradient difference of the corresponding pixel is ≥ the mean value of the standard deviation value of the gradient difference, then the corresponding pixel is judged to be a candidate edge pixel, and the grayscale value of the corresponding pixel is set to the sum of the corresponding gradient value and the corresponding standard deviation value of the gradient difference; wherein the range of the corresponding gradient value and the corresponding standard deviation value of the gradient difference are both [0,255]; If the gradient value corresponding to any pixel in the grayscale image is less than the gradient value mean, or the gradient difference standard deviation value of the corresponding pixel is less than the gradient difference standard deviation value mean, the corresponding pixel is judged to be a noise point, and the grayscale value of the corresponding pixel is set to 0.

4. The method for measuring the size of mineral rocks according to claim 3, characterized in that: If so, then a number of corresponding associated pixels on the candidate edge fusion map are voted, and at the same time, a number of adjacent pixels of the associated pixels in a direction perpendicular to the gradient are also voted; According to the number of votes of any pixel in the candidate edge fusion image, judging whether the corresponding pixel is a candidate edge fusion pixel includes: According to the grayscale image, a multi-scale image pyramid is created to obtain a first scale-level grayscale image, a second scale-level grayscale image, ..., an Lth scale-level grayscale image, ..., an Lth scale-level grayscale image, ..., an Lth scale-level grayscale image m Scale level grayscale image; L m represents the maximum scale level of the multi-scale image pyramid; If any pixel (a, b) in the Lth scale level grayscale image is a candidate edge pixel, then the corresponding associated pixel (a×2 L ,b×2 L ) is voted, and at the same time, the associated pixel (a×2 L ,b×2 L ) The L neighboring pixels perpendicular to the gradient direction are also voted; The number of votes for any pixel on the candidate edge fusion map To conduct statistics; like ,in represents a round-up operation, the corresponding pixel on the candidate edge fusion image is the candidate edge fusion pixel, and the grayscale value of the corresponding pixel is set to the sum of the gradient value of the corresponding pixel in the grayscale image and the standard deviation value of the gradient difference.

5. The method for measuring the size of mineral rocks according to claim 4, characterized in that: The joint calibration of the camera and the laser radar includes: Using a 3D laser radar in a multimodal 3D environment perception system to collect multiple sets of 3D laser point clouds containing black and white checkerboard calibration plates in different postures; using a camera in the multimodal 3D environment perception system to collect multiple sets of 2D images containing black and white checkerboard calibration plates in different postures; wherein each set of 3D laser point clouds and 2D images are collected at the same sampling time; Using multiple sets of two-dimensional images containing a checkerboard calibration plate in different poses, the camera intrinsic parameter matrix is ​​calculated based on Zhang Zhengyou's calibration method. At the same time, through the intrinsic parameter calibration, the pose relationship between the calibration plate coordinate system and the camera coordinate system in different poses is calculated; Using the external parameter calibration method of 3D laser radar and camera, the linear equations of line-surface geometric constraints and surface-surface geometric constraints are jointly constructed, and the initial external parameter matrix is ​​solved using the least squares method; A global error consisting of the pixel projection error caused by the camera intrinsic calibration and the laser point vertical distance error caused by the initial extrinsic calibration is constructed. The Levenberg-Marquardt method is used for nonlinear global optimization solution to complete the final extrinsic calibration.

6. The method for measuring the size of mineral rocks according to claim 5, characterized in that: The calculation formula of the calibration coefficient is: ； in, is the length of the first rectangle; is the width of the first rectangle; is the length of the second rectangle; is the width of the second rectangle; is the calibration coefficient; The unit is cm / pixel.

7. The method for measuring the size of mineral rocks according to claim 6, characterized in that: The calculation formula for the block size of the rock in the ore rock segmentation diagram is: ； in, The number of pixels in the ore rock segmentation map is The size of the rock mass; is the calibration factor.

8. A device for measuring the size of mineral rocks, characterized in that: include: A first computing module is used to obtain a color image of the ore rock taken by a camera and convert the color image into a grayscale image; According to the grayscale image, a gradient value corresponding to any pixel in the grayscale image is calculated; According to the gradient value, a standard deviation value of the gradient difference of the corresponding pixel is calculated; The first determination module is used to create a candidate edge fusion map; according to the gradient value and the gradient difference standard deviation value corresponding to any pixel in the grayscale image, determine whether the corresponding pixel is a candidate edge pixel; if so, then the corresponding several associated pixels on the candidate edge fusion map are voted, and at the same time, several adjacent pixels of the associated pixel in the direction perpendicular to the gradient are also voted; according to the number of votes of any pixel in the candidate edge fusion map, determine whether the corresponding pixel is a candidate edge fusion pixel; according to each of the candidate edge fusion pixels and the candidate edge fusion map, obtain an intermediate edge fusion map; perform lag connection on the intermediate edge fusion map to obtain a final edge fusion map; process the final edge fusion map by a watershed algorithm to obtain a mineral rock segmentation map; The second determination module is used to perform internal parameter calibration on the camera to obtain an internal parameter calibration matrix; perform joint calibration on the camera and the laser radar to obtain an external parameter calibration matrix; obtain a point cloud image mapping relationship according to the internal parameter calibration matrix and the external parameter calibration matrix; map the three-dimensional point cloud of the ore rock collected by the laser radar and the ore rock segmentation map according to the point cloud image mapping relationship to obtain a ore rock block segmentation point cloud; perform plane fitting on the ore rock block segmentation point cloud and project it to the fitting plane to obtain a ore rock block segmentation plane point cloud; perform sparsity screening on each rock block in the ore rock block segmentation plane point cloud to obtain a high-density target rock block point cloud; The second calculation module is used to draw a first minimum circumscribed rectangle for the high-density target rock block point cloud in the mineral rock block segmentation plane point cloud to obtain a first rectangle length and a first rectangle width; in the mineral rock segmentation map, draw a second minimum circumscribed rectangle for the rock block image corresponding to the high-density target rock block point cloud to obtain a second rectangle length and a second rectangle width; calculate a calibration coefficient based on the first rectangle length, the first rectangle width, the second rectangle length and the second rectangle width; calculate the blockiness of the corresponding rock block based on the calibration coefficient and the number of pixels corresponding to each rock block in the mineral rock segmentation map.

9. An electronic device, characterized in that: include: at least one processor; A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can execute the mineral rock block size measurement method described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the method for measuring the mineral rock fragmentation according to any one of claims 1-7.

Images