Ore crushing point selection method and device and terminal

Abstract

The invention discloses an ore crushing point selection method and device and a terminal, and belongs to the technical field of ore crushing, and the method comprises the steps: obtaining the final target point cloud data of an ore based on image data and point cloud data through a yolov8 target detection model; and based on the final ore target point cloud data, utilizing a Delaunay triangulation algorithm to obtain final ore crushing point data. According to the method, the crusher can accurately position the large-size ore in the operation process and accurately select the crushing points with reasonable positions and crushing angles according to the surface information of the ore, the point cloud of the large-size ore can be accurately extracted in a complex crushing environment, and the point cloud reconstruction speed and reliability are improved.

Description

Technical Field

[0001] The invention discloses a method, a device and a terminal for selecting ore crushing points, and belongs to the technical field of ore crushing. Background Art

[0002] For unmanned crushers for mining rock crushing operations, since there is no driver to operate, the machine needs to use the environmental information obtained by sensors to accurately locate large-sized ores and accurately select the crushing points. The selection of ore crushing points is not only a key factor affecting the crushing effect, crushing efficiency and ore utilization, but also a prerequisite for formulating crushing strategies, because after each crushing, the next crushing strategy needs to be adjusted based on the crushing point information of all ores to better perform the operation.

[0003] The methods for selecting crushing points in existing research results are mainly to reconstruct the 3D point cloud of the ore through a binocular camera and calculate the normal vector of each point in the ore point cloud to select a surface parallel to the ground or to fit a relatively flat surface using RANSAC. However, these methods have certain problems in practical applications. First, the performance of the binocular camera is very sensitive to lighting conditions and the reconstruction process requires a lot of computing resources. Second, the shape of the ore is diverse. The best crushing point of some ores is not necessarily on a surface parallel to the ground, and the accuracy of the RANSAC fitting plane is not very high. If the shape of the ore surface is irregular, the result of RANSAC fitting will be very poor. Third, it does not take into account whether the position of the crushing point and the crushing angle relative to the position of the crusher are reasonable. It is a difficult problem to accurately locate large-sized ores and select crushing points with reasonable positions. In addition, the ore may be mixed with other debris and blocked, and the shape and position of the ore are different, making it impossible for the system to accurately select the crushing point.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method, device and terminal for selecting ore crushing points, so as to at least solve the technical problem that the crushing points cannot be accurately selected.

[0006] According to one aspect of an embodiment of the present invention, a method for selecting an ore crushing point is provided, which is applied to an ore crushing point selection system. The ore crushing point selection system includes roadside equipment, and a monocular camera and a laser radar are respectively provided on the roadside equipment. The monocular camera and the laser radar are respectively electrically connected to a terminal. The monocular camera is used to collect image data and send it to the terminal, and the laser radar is used to collect point cloud data and send it to the terminal. The terminal obtains the image data and the point cloud data and executes the ore crushing point selection method, including:

[0007] Based on the image data and point cloud data, the yolov8 target detection model is used to obtain the final target point cloud data of the ore;

[0008] Based on the final ore target point cloud data, the final ore crushing point data is obtained by using the Delaunay triangulation algorithm.

[0009] Further, based on the image data and the point cloud data, the yolov8 target detection model is used to obtain the final target point cloud data of the ore, including:

[0010] Based on the image data, the yolov8 target detection model is used to perform target recognition and instance segmentation, and all pixel points on the instance segmentation object contour within the yolo prediction box with a side length greater than a certain length are obtained;

[0011] Calculating the two-dimensional convex hull corresponding to all pixel points on the contours of the multiple instance segmentation objects;

[0012] After accumulating 50 frames of the point cloud data, project them onto a two-dimensional convex hull formed by all pixel points on the contours of the multiple instance segmentation objects and extract the point cloud data projected within the multiple two-dimensional convex hulls;

[0013] The plurality of point cloud data extracted above are subjected to point cloud denoising, downsampling, dbscan clustering processing and 3D bounding box generation respectively to obtain a 3D bounding box whose length, width and height are greater than a certain threshold;

[0014] Projecting eight vertices on the 3D bounding boxes of the plurality of clustering results that meet the conditions onto the image to form 2D bounding boxes, and calculating a plurality of intersection-over-union ratios of the plurality of 2D bounding boxes and the prediction boxes of the corresponding instance segmentation objects;

[0015] Obtaining a maximum intersection-and-union ratio according to the plurality of intersection-and-union ratios, and obtaining corresponding target point cloud data according to the maximum intersection-and-union ratio;

[0016] According to the target point cloud data, it is determined whether the distance between each point of the target point cloud data and the centroid of the target point cloud is greater than a distance threshold to delete outliers and obtain final target point cloud data.

[0017] Furthermore, based on the final ore target point cloud data, the Delaunay triangulation algorithm is used to obtain the final ore crushing point data, including:

[0018] Based on the final ore target point cloud data, multiple three-dimensional convex hulls of the point cloud data of multiple large-size ores are calculated respectively, the polygons on the multiple three-dimensional convex hulls are decomposed into multiple triangles, a certain number of random points are generated inside each triangle according to the area size, and only the random points located above the centroid of the target point cloud are retained;

[0019] Downsampling and homogenizing the random points corresponding to the plurality of large-sized ores to obtain the homogenized random points corresponding to the plurality of large-sized ores;

[0020] Accumulate 10 frames of homogenized random points corresponding to the plurality of large-size ores, and perform ICP registration on the random points of each frame of the 10 frames of random points and the random points of the previous and next frames, and perform Delaunay triangulation on the most stable frame of random points using the Delaunay triangulation algorithm to obtain a plurality of new triangles;

[0021] According to the multiple new triangles, multiple candidate fragmentation points are obtained;

[0022] An MDH parameterized model of the crusher is established, evaluation indicators of the candidate crushing points are obtained based on the candidate crushing points, and an optimal crushing point is obtained according to the evaluation indicators of the candidate crushing points.

[0023] Furthermore, the evaluation index calculation formula of the candidate breakpoint is as follows:

[0024] R=a×Ab×d (1)

[0025] Among them: a and b are empirical coefficients, A is the area of ​​the region where the breakup point is located, and d is the distance from the normal vector of the breakup point to the centroid of the point cloud.

[0026] According to another aspect of an embodiment of the present invention, there is also provided a device for selecting ore crushing points, comprising:

[0027] A target point cloud acquisition module is used to obtain the final target point cloud data of the ore based on the image data and the point cloud data using the yolov8 target detection model;

[0028] The crushing point acquisition module is used to obtain the final crushing point data of the ore based on the final ore target point cloud data using the Delaunay triangulation algorithm.

[0029] Furthermore, the target point cloud acquisition module is also used for:

[0030] Based on the image data, the yolov8 target detection model is used to perform target recognition and instance segmentation, and all pixel points on the instance segmentation object contour within the yolo prediction box with a side length greater than a certain length are obtained;

[0031] Calculating the two-dimensional convex hull corresponding to all pixel points on the contours of the multiple instance segmentation objects;

[0032] After accumulating 50 frames of the point cloud data, project them onto a two-dimensional convex hull formed by all pixel points on the contours of the multiple instance segmentation objects and extract the point cloud data projected within the multiple two-dimensional convex hulls;

[0033] The plurality of point cloud data extracted above are subjected to point cloud denoising, downsampling, dbscan clustering processing and 3D bounding box generation respectively to obtain a 3D bounding box whose length, width and height are greater than a certain threshold;

[0034] Projecting eight vertices on the 3D bounding boxes of the plurality of clustering results that meet the conditions onto the image to form 2D bounding boxes, and calculating a plurality of intersection-over-union ratios of the plurality of 2D bounding boxes and the prediction boxes of the corresponding instance segmentation objects;

[0035] Obtaining a maximum intersection-and-union ratio according to the plurality of intersection-and-union ratios, and obtaining corresponding target point cloud data according to the maximum intersection-and-union ratio;

[0036] According to the target point cloud data, it is determined whether the distance between each point of the target point cloud data and the centroid of the target point cloud is greater than a distance threshold to delete outliers and obtain final target point cloud data.

[0037] Furthermore, the breaking point acquisition module is also used for:

[0038] Based on the final ore target point cloud data, multiple three-dimensional convex hulls of the point cloud data of multiple large-size ores are calculated respectively, the polygons on the multiple three-dimensional convex hulls are decomposed into multiple triangles, a certain number of random points are generated inside each triangle according to the area size, and only the random points located above the centroid of the target point cloud are retained;

[0039] Downsampling and homogenizing the random points corresponding to the plurality of large-sized ores to obtain the homogenized random points corresponding to the plurality of large-sized ores;

[0040] Accumulate 10 frames of homogenized random points corresponding to the plurality of large-size ores, and perform ICP registration on the random points of each frame of the 10 frames of random points and the random points of the previous and next frames, and perform Delaunay triangulation on the most stable frame of random points using the Delaunay triangulation algorithm to obtain a plurality of new triangles;

[0041] According to the multiple new triangles, multiple candidate fragmentation points are obtained;

[0042] An MDH parameterized model of the crusher is established, evaluation indicators of the candidate crushing points are obtained based on the candidate crushing points, and an optimal crushing point is obtained according to the evaluation indicators of the candidate crushing points.

[0043] According to another aspect of an embodiment of the present invention, a terminal is further provided, comprising: a memory storing an executable program; and a processor for running the program, wherein when the program is running, the method for selecting ore crushing points in each embodiment of the present invention is executed.

[0044] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the ore crushing point selection method in each embodiment of the present invention.

[0045] According to another aspect of an embodiment of the present invention, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the method for selecting ore crushing points in each embodiment of the present invention is implemented.

[0046] The beneficial effects of the present invention are:

[0047] The present invention provides a method, device and terminal for selecting ore crushing points. The method, device and terminal fuse the information sensed by a monocular camera and a laser radar, obtain the final target point cloud data of the ore based on the image data and the point cloud data by using the yolov8 target detection model, and obtain the final crushing point data of the ore based on the final target point cloud data of the ore by using the Delaunay triangulation algorithm. The method enables the crusher to accurately locate large-sized ores during operation and accurately select crushing points with reasonable positions and crushing angles according to the surface information of the ore. The method not only can accurately extract the point cloud of large-sized ores in a complex crushing environment, but also improves the speed and reliability of point cloud reconstruction.

[0048] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 The present invention is a flow chart of a method for selecting ore crushing points according to an exemplary embodiment.

[0050] Figure 2 The present invention is a flow chart of a method for selecting ore crushing points according to an exemplary embodiment.

[0051] Figure 3 It is a schematic diagram of the hardware configuration of a system for selecting ore crushing points according to an exemplary embodiment.

[0052] Figure 4 It is a result diagram of yolov8 target detection and instance segmentation in a method for selecting ore crushing points according to an exemplary embodiment.

[0053] Figure 5The present invention is a target point cloud diagram in a method for selecting ore crushing points according to an exemplary embodiment.

[0054] Figure 6 It is a rendering of the effect of triangle reconstruction in a method for selecting ore crushing points according to an exemplary embodiment.

[0055] Figure 7 The present invention is a diagram showing the effect of candidate crushing surfaces in a method for selecting ore crushing points according to an exemplary embodiment.

[0056] Figure 8 Schematic diagram of the geometric relationship of the inverse solution of the kinematics of a crusher in a method for selecting ore crushing points according to an exemplary embodiment.

[0057] Fig. 9 2 is a schematic diagram of crushing points in a method for selecting ore crushing points according to an exemplary embodiment.

[0058] Fig.10 A schematic block diagram of the structure of a device for selecting ore crushing points is shown according to an exemplary embodiment.

[0059] Fig.11 A schematic block diagram of a terminal structure is shown according to an exemplary embodiment. DETAILED DESCRIPTION

[0060] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. 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.

[0061] In the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they cannot be understood as limitations on the present invention.

[0062] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0063] The embodiment of the present invention provides a method for selecting ore crushing points. The method is implemented by a terminal. The terminal may be a desktop computer or a laptop computer, etc. The terminal at least includes a CPU, etc.

[0064] Embodiment 1

[0065] Figure 1 and 2 The present invention is a flow chart of a method for selecting an ore crushing point according to an exemplary embodiment. The method is used in a terminal and comprises the following steps:

[0066] The ore crushing point selection method is applied to the ore crushing point selection system, such as Figure 3 As shown, the ore crushing point selection system includes a roadside device 3, on which a monocular camera 1 and a laser radar 2 are respectively installed. The monocular camera 1 and the laser radar 2 are respectively electrically connected to the terminal. The monocular camera 1 is used to collect image data and send it to the terminal. The laser radar 2 is used to collect point cloud data and send it to the terminal. The terminal obtains the image data and point cloud data and executes the ore crushing point selection method. The terminal preferably uses an edge computing box. The specific steps of the ore crushing point selection method are as follows:

[0067] Step S10, based on the image data and point cloud data, using the yolov8 target detection model, obtain the final target point cloud data of the ore, the specific content is as follows:

[0068] like Figure 4 As shown, based on the image data, the yolov8 target detection model is used to perform target recognition and instance segmentation, and all pixel points on the contour of multiple instance segmentation objects of the yolo prediction box with a side length greater than a certain length are obtained.

[0069] The external parameter matrix obtained by radar and camera calibration for all pixel points on the contours of multiple instance segmentation objects is projected into the lidar coordinate system. Since pixel points have no depth information, the z value of each pixel point is continuously iterated within a certain range to form many conical areas. The radar point cloud within the conical area is the point cloud of the instance segmentation object and other debris. The original radar point cloud is accumulated for 50 frames, and the two-dimensional convex hull of all pixel points on the contours of multiple instance segmentation objects is calculated; after accumulating 50 frames of point cloud data, it is projected onto the two-dimensional convex hull of all pixel points on the contours of multiple instance segmentation objects and the point cloud data projected within the multiple two-dimensional convex hulls is extracted.

[0070] The point cloud data in multiple two-dimensional convex hulls are downsampled and denoised by statistical filtering, and then subjected to dbscan clustering processing and 3D bounding box generation to obtain a 3D bounding box with a length, width and height greater than a certain threshold;

[0071] Project the eight vertices on the 3D bounding boxes of the clustering results that meet the conditions onto the image to form a 2D bounding box, and calculate the multiple intersection-and-union ratios of the multiple 2D bounding boxes and the prediction boxes of the corresponding instance segmentation objects; obtain the maximum intersection-and-union ratio based on the multiple intersection-and-union ratios, and obtain the corresponding target point cloud data based on the maximum intersection-and-union ratio. The rest are the debris point cloud data in the conical area corresponding to this instance segmentation object. According to the target point cloud data, determine whether the distance between each point of the target point cloud data and the centroid of the target point cloud is greater than the distance threshold to delete the outliers and obtain the final target point cloud data, such as Figure 5 shown.

[0072] Step S20, based on the final ore target point cloud data, using the Delaunay triangulation algorithm to obtain the final ore crushing point data, the specific steps are as follows:

[0073] Based on the final ore target point cloud data, multiple three-dimensional convex hulls of the point cloud data of multiple large-size ores are calculated respectively, the polygons on the multiple three-dimensional convex hulls are decomposed into multiple triangles, and a certain number of random points are generated in the multiple triangles using barycentric coordinates according to the area size of each triangle, and only the random points above the centroid of the point cloud are retained.

[0074] The random points of the triangles corresponding to multiple large-size ores are downsampled and homogenized to obtain the homogenized random points corresponding to the multiple large-size ores. That is, the random points corresponding to each large-size ore are downsampled, and then according to whether the local density of each random point reaches a certain threshold, some points are added or deleted in the neighborhood of each random point to homogenize all the random points to obtain the homogenized random points corresponding to the multiple large-size ores.

[0075] The Delaunay triangulation algorithm is used to perform Delaunay triangulation on the homogenized random points corresponding to multiple large-sized ores, and lines are used to connect the three vertices of each triangle to visualize the results of triangle reconstruction, such as Figure 6 As shown in the figure. Since the number and position of points scanned by the laser radar in each frame are inconsistent, the homogenized random points corresponding to each large-size ore are accumulated for 10 frames, and the random points in each frame of these 10 frames are ICP-aligned with the random points in the previous and next frames. The most stable frame is selected and Delaunay triangulation is performed on the random points in the most stable frame to obtain the index values ​​of the three vertices corresponding to each triangle. In this way, many plane triangles are used to fit the outer surface of the ore to obtain multiple new triangles.

[0076] Based on multiple new triangles, multiple candidate breakpoints are obtained. The specific steps are as follows:

[0077] Step 1. Take any triangle as the central triangle. When the angles between the normal vectors of the three triangles adjacent to the central triangle and the normal vector of the central triangle are all less than 10 degrees, include these four triangles into a region. Step 2. Include the triangles adjacent to this region and whose normal vectors have an angle less than 10 degrees with the normal vector of the central triangle into this region. Step 3. Repeat the operation in step 2 5 times, that is, expand the region 5 times to obtain the final region. Step 4. Calculate the area of ​​each triangle in the final region. The area of ​​the final region is the sum of the areas of all the triangles inside it. If the area of ​​the final region is larger than 5 times the area of ​​the hammer head of the breaker, then the region can be used as a candidate crushing surface. Figure 7 As shown, all triangles in the area are marked to ensure that each triangle cannot be included in two different areas repeatedly. Step 5, then select other unmarked triangles as central triangles to perform steps 1 to 4, and use the centroid of the central triangle of each area as the candidate crushing point of the ore, and the normal vector direction of the central triangle is the crushing direction of the candidate crushing point.

[0078] Establish an MDH parameterized model of the crusher, obtain evaluation indicators of multiple candidate crushing points based on multiple candidate crushing points, and obtain the optimal crushing point according to the evaluation indicators of the multiple candidate crushing points. The specific steps are as follows:

[0079] Establish the MDH parametric model of the crusher and convert the crushing direction of each candidate crushing point into the crushing hammer posture angle And transform the coordinates of the candidate breakpoint relative to the lidar into the coordinates relative to the base coordinate system of the MDH parameterized model (x p ,y p , z p ). Convert the crushing direction into the crushing hammer posture angle The process is divided into several steps: Since the normal vector of the candidate shatter point It is difficult to be exactly on the plane α passing through the origin of the base coordinate system and the point and perpendicular to the xoy plane of the base coordinate system. Therefore, if the normal vector of the candidate shatter point If the angle with plane α is less than 10 degrees, the normal vector Projecting onto plane α to get the normal vector In order to make the crushing direction of the breaker as close as possible to the normal vector of the candidate crushing point direction, it is necessary to make the crushing direction of the breaker and the normal vector The angle is the smallest, and the crushing direction of the breaker is Figure 8 and 9 In The coordinates of O4 are:

[0080]

[0081] Rotation joint angle θ 1 for:

[0082]

[0083] therefore calculate With normal vector The angle of is an unknown quantity, so Within a certain range, traverse all values ​​within the range, calculate the angle corresponding to each different value, and select the value corresponding to the minimum angle as

[0084] ) is the final Use the inverse kinematic solution to convert (x p ,y p , z p , ) is transformed into (θ 1 ,θ 2 ,θ 3 ,θ 4 ), where θ 1 is the rotation joint angle, θ 2 is the boom joint angle, θ 3 is the stick joint angle, θ 4 is the hammer joint angle. Then (θ 1 ,θ 2 ,θ 3 ,θ 4 ) is converted to (λ 1 ,λ 2 ,λ 3 ,λ 4 ), where λ 1 is the rotation angle of the rotary motor, λ 2 is the length of the boom hydraulic cylinder, λ 3 is the length of the boom hydraulic cylinder, λ 4 is the length of the hydraulic cylinder of the breaker. 1 ,θ 2 ,θ 3 ,θ 4 ) and (λ 1 ,λ 2 ,λ 3 ,λ 4 ) is within the specified angle and length range. If so, it proves that the breaker can break at a certain position at the specified angle. The calculation formula of the evaluation index R of each breaking point is as follows:

[0085] R=a×Ab×d (3)

[0086] Where a and b are empirical coefficients, A is the area of ​​the broken point, and d is the normal vector The distance to the centroid of the ore point cloud. a and b are integers of hundreds or thousands. The specific values ​​depend on the size of A and d. It is necessary to ensure that the results of a×A and b×d are in the same order of magnitude. The smaller d is, the easier it is for the ore to be split into several pieces, rather than just breaking the surface part or not meeting the size requirements after crushing; the larger A is, it means that the area is larger after expanding the crushing area 5 times, which means that the area centered on this crushing point has a higher flatness, the crushing process will be more stable, and the fault tolerance will be greater. Calculate the evaluation index of each candidate crushing point with a reasonable position, and use the crushing point with the highest evaluation index as the final crushing point of the ore.

[0087] Embodiment 2

[0088] Fig.10 A device for selecting ore crushing points according to an exemplary embodiment includes:

[0089] The target point cloud acquisition module 210 is used to obtain the final target point cloud data of the ore based on the image data and the point cloud data using the yolov8 target detection model;

[0090] The crushing point acquisition module 220 is used to obtain the final crushing point data of the ore based on the final ore target point cloud data using the Delaunay triangulation algorithm.

[0091] Furthermore, the target point cloud acquisition module 210 is also used for:

[0092] Based on the image data, the yolov8 target detection model is used to perform target recognition and instance segmentation, and all pixel points on the instance segmentation object contour within the yolo prediction box with a side length greater than a certain length are obtained;

[0093] Calculating the two-dimensional convex hull corresponding to all pixel points on the contours of the multiple instance segmentation objects;

[0094] After accumulating 50 frames of the point cloud data, project them onto a two-dimensional convex hull formed by all pixel points on the contours of the multiple instance segmentation objects and extract the point cloud data projected within the multiple two-dimensional convex hulls;

[0095] The plurality of point cloud data extracted above are subjected to point cloud denoising, downsampling, dbscan clustering processing and 3D bounding box generation respectively to obtain a 3D bounding box whose length, width and height are greater than a certain threshold;

[0096] Projecting eight vertices on the 3D bounding boxes of the plurality of clustering results that meet the conditions onto the image to form 2D bounding boxes, and calculating a plurality of intersection-over-union ratios of the plurality of 2D bounding boxes and the prediction boxes of the corresponding instance segmentation objects;

[0097] Obtaining a maximum intersection-and-union ratio according to the plurality of intersection-and-union ratios, and obtaining corresponding target point cloud data according to the maximum intersection-and-union ratio;

[0098] According to the target point cloud data, it is determined whether the distance between each point of the target point cloud data and the centroid of the target point cloud is greater than a distance threshold to delete outliers and obtain final target point cloud data.

[0099] Furthermore, the breaking point acquisition module 220 is also used for:

[0100] Based on the final ore target point cloud data, multiple three-dimensional convex hulls of the point cloud data of multiple large-size ores are calculated respectively, the polygons on the multiple three-dimensional convex hulls are decomposed into multiple triangles, a certain number of random points are generated inside each triangle according to the area size, and only the random points located above the centroid of the target point cloud are retained;

[0101] Downsampling and homogenizing the random points corresponding to the plurality of large-sized ores to obtain the homogenized random points corresponding to the plurality of large-sized ores;

[0102] Accumulate 10 frames of homogenized random points corresponding to the plurality of large-size ores, and perform ICP registration on the random points of each frame of the 10 frames of random points and the random points of the previous and next frames, and perform Delaunay triangulation on the most stable frame of random points using the Delaunay triangulation algorithm to obtain a plurality of new triangles;

[0103] According to the multiple new triangles, multiple candidate fragmentation points are obtained;

[0104] An MDH parameterized model of the crusher is established, evaluation indicators of the candidate crushing points are obtained based on the candidate crushing points, and an optimal crushing point is obtained according to the evaluation indicators of the candidate crushing points.

[0105] This application fuses the information sensed by the monocular camera and the laser radar, obtains the final target point cloud data of the ore based on the image data and point cloud data using the yolov8 target detection model, and obtains the final crushing point data of the ore based on the final ore target point cloud data using the Delaunay triangulation algorithm. This enables the crusher to accurately locate large-sized ores during operation and accurately select crushing points with reasonable positions and crushing angles based on the surface information of the ore. It can not only accurately extract the point cloud of large-sized ores in complex crushing environments, but also improve the speed and reliability of point cloud reconstruction.

[0106] Embodiment 3

[0107] Fig.11 300 is a block diagram of a terminal provided in an embodiment of the present application, and the terminal may be a terminal in the above embodiment. The terminal 300 may be a portable mobile terminal, such as a smart phone or a tablet computer. The terminal 300 may also be referred to as a user equipment, a portable terminal, or other names.

[0108] Typically, the terminal 300 includes a processor 301 and a memory 302 .

[0109] The processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 301 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0110] The memory 302 may include one or more computer-readable storage media, which may be tangible and non-transitory. The memory 302 may also include a high-speed random access memory and a non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 302 is used to store at least one instruction, which is used to be executed by the processor 301 to implement a method for selecting an ore crushing point provided in the present application.

[0111] In some embodiments, the terminal 300 may further include: a peripheral device interface 303 and at least one peripheral device. Specifically, the peripheral device includes: at least one of a radio frequency circuit 304 , a touch screen 305 , a camera 306 , an audio circuit 307 , a positioning component 308 and a power supply 309 .

[0112] The peripheral device interface 303 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 301 and the memory 302. In some embodiments, the processor 301, the memory 302, and the peripheral device interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the peripheral device interface 303 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0113] The radio frequency circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 304 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 304 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 304 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 304 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 304 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0114] The touch display screen 305 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos and any combination thereof. The touch display screen 305 also has the ability to collect touch signals on the surface or above the surface of the touch display screen 305. The touch signal can be input to the processor 301 as a control signal for processing. The touch display screen 305 is used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the touch display screen 305 can be one, and the front panel of the terminal 300 is set; in other embodiments, the touch display screen 305 can be at least two, which are respectively set on different surfaces of the terminal 300 or are folded; in some other embodiments, the touch display screen 305 can be a flexible display screen, which is set on the curved surface or folded surface of the terminal 300. Even, the touch display screen 305 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The touch display screen 305 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0115] The camera assembly 306 is used to capture images or videos. Optionally, the camera assembly 306 includes a front camera and a rear camera. Typically, the front camera is used to realize video calls or selfies, and the rear camera is used to realize the shooting of photos or videos. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, and a wide-angle camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, and the fusion of the main camera and the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting functions. In some embodiments, the camera assembly 306 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0116] The audio circuit 307 is used to provide an audio interface between the user and the terminal 300. The audio circuit 307 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 301 for processing, or input them into the radio frequency circuit 304 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal 300. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 301 or the radio frequency circuit 304 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 307 may also include a headphone jack.

[0117] The positioning component 308 is used to locate the current geographical location of the terminal 300 to implement navigation or LBS (Location Based Service). The positioning component 308 can be a positioning component based on the US GPS (Global Positioning System), China's Beidou system or Russia's Galileo system.

[0118] The power supply 309 is used to power various components in the terminal 300. The power supply 309 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 309 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0119] In some embodiments, the terminal 300 further includes one or more sensors 310 , including but not limited to: an acceleration sensor 311 , a gyroscope sensor 312 , a pressure sensor 313 , a fingerprint sensor 314 , an optical sensor 315 , and a proximity sensor 316 .

[0120] The acceleration sensor 311 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the terminal 300. For example, the acceleration sensor 311 can be used to detect the components of gravity acceleration on the three coordinate axes. The processor 301 can control the touch display screen 305 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 311. The acceleration sensor 311 can also be used for collecting game or user motion data.

[0121] The gyro sensor 312 can detect the body direction and rotation angle of the terminal 300. The gyro sensor 312 can cooperate with the acceleration sensor 311 to collect the user's 3D (3 Dimensions) action on the terminal 300. The processor 301 can implement the following functions based on the data collected by the gyro sensor 312: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0122] The pressure sensor 313 can be set on the side frame of the terminal 300 and / or the lower layer of the touch display screen 305. When the pressure sensor 313 is set on the side frame of the terminal 300, it can detect the user's holding signal of the terminal 300, and perform left and right hand recognition or shortcut operation according to the holding signal. When the pressure sensor 313 is set on the lower layer of the touch display screen 305, it can control the operability control on the UI interface according to the user's pressure operation on the touch display screen 305. The operability control includes at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0123] The fingerprint sensor 314 is used to collect the user's fingerprint to identify the user's identity based on the collected fingerprint. When the user's identity is identified as a trusted identity, the processor 301 authorizes the user to perform relevant sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, paying, and changing settings. The fingerprint sensor 314 can be set on the front, back, or side of the terminal 300. When a physical button or a manufacturer logo is set on the terminal 300, the fingerprint sensor 314 can be integrated with the physical button or the manufacturer logo.

[0124] The optical sensor 315 is used to collect the ambient light intensity. In one embodiment, the processor 301 can control the display brightness of the touch display screen 305 according to the ambient light intensity collected by the optical sensor 315. Specifically, when the ambient light intensity is high, the display brightness of the touch display screen 305 is increased; when the ambient light intensity is low, the display brightness of the touch display screen 305 is reduced. In another embodiment, the processor 301 can also dynamically adjust the shooting parameters of the camera assembly 306 according to the ambient light intensity collected by the optical sensor 315.

[0125] The proximity sensor 316, also called a distance sensor, is usually arranged on the front of the terminal 300. The proximity sensor 316 is used to collect the distance between the user and the front of the terminal 300. In one embodiment, when the proximity sensor 316 detects that the distance between the user and the front of the terminal 300 is gradually decreasing, the processor 301 controls the touch display screen 305 to switch from the screen-on state to the screen-off state; when the proximity sensor 316 detects that the distance between the user and the front of the terminal 300 is gradually increasing, the processor 301 controls the touch display screen 305 to switch from the screen-off state to the screen-on state.

[0126] Those skilled in the art will understand that Figure 3 The structure shown in the figure does not constitute a limitation on the terminal 300, and the terminal 300 may include more or less components than those shown in the figure, or combine some components, or adopt a different component arrangement.

[0127] Embodiment 4

[0128] In an exemplary embodiment, a computer-readable storage medium is also provided, on which a computer program is stored. When the program is executed by a processor, a method for selecting an ore crushing point is implemented as provided in all the inventive embodiments of the present application.

[0129] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, 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 thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0130] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0131] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0132] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0133] Embodiment 5

[0134] In an exemplary embodiment, an application product is also provided, including one or more instructions, which can be executed by the processor 301 of the above-mentioned device to complete the above-mentioned method for selecting a ore crushing point.

[0135] Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and the embodiments. It can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily realized. Therefore, without departing from the general concept defined by the claims and equivalent scope, the present invention is not limited to the specific details and the illustrations shown and described here.

Claims

1. A method for selecting an ore crushing point, applied to an ore crushing point selection system, the ore crushing point selection system comprising a roadside device (3), the roadside device (3) being provided with a monocular camera (1) and a laser radar (2), the monocular camera (1) and the laser radar (2) being electrically connected to a terminal, the monocular camera (1) being used to collect image data and send it to the terminal, the laser radar (2) being used to collect point cloud data and send it to the terminal, the terminal acquiring the image data and the point cloud data and executing the method for selecting an ore crushing point, characterized in that: include: Based on the image data and point cloud data, the yolov8 target detection model is used to obtain the final target point cloud data of the ore; Based on the final ore target point cloud data, the final ore crushing point data is obtained by using the Delaunay triangulation algorithm.

2. The method for selecting ore crushing points according to claim 1, characterized in that: Based on the image data and point cloud data, the yolov8 target detection model is used to obtain the final target point cloud data of the ore, including: Based on the image data, the yolov8 target detection model is used to perform target recognition and instance segmentation, and all pixel points on the instance segmentation object contour within the yolo prediction box with a side length greater than a certain length are obtained; Calculating the two-dimensional convex hull corresponding to all pixel points on the contours of the multiple instance segmentation objects; After accumulating 50 frames of the point cloud data, project them onto a two-dimensional convex hull formed by all pixel points on the contours of the multiple instance segmentation objects and extract the point cloud data projected within the multiple two-dimensional convex hulls; The plurality of point cloud data extracted above are subjected to point cloud denoising, downsampling, dbscan clustering processing and 3D bounding box generation respectively to obtain a 3D bounding box whose length, width and height are greater than a certain threshold; Projecting eight vertices on the 3D bounding boxes of the plurality of clustering results that meet the conditions onto the image to form 2D bounding boxes, and calculating a plurality of intersection-over-union ratios of the plurality of 2D bounding boxes and the prediction boxes of the corresponding instance segmentation objects; Obtaining a maximum intersection-and-union ratio according to the plurality of intersection-and-union ratios, and obtaining corresponding target point cloud data according to the maximum intersection-and-union ratio; According to the target point cloud data, it is determined whether the distance between each point of the target point cloud data and the centroid of the target point cloud is greater than a distance threshold to delete outliers and obtain final target point cloud data.

3. The method for selecting ore crushing points according to claim 1, characterized in that: Based on the final ore target point cloud data, the Delaunay triangulation algorithm is used to obtain the final ore crushing point data, including: Based on the final ore target point cloud data, multiple three-dimensional convex hulls of the point cloud data of multiple large-size ores are calculated respectively, the polygons on the multiple three-dimensional convex hulls are decomposed into multiple triangles, a certain number of random points are generated inside each triangle according to the area size, and only the random points located above the centroid of the target point cloud are retained; Downsampling and homogenizing the random points corresponding to the plurality of large-sized ores to obtain the homogenized random points corresponding to the plurality of large-sized ores; Accumulate 10 frames of homogenized random points corresponding to the plurality of large-size ores, and perform ICP registration on the random points of each frame of the 10 frames of random points and the random points of the previous and next frames, and perform Delaunay triangulation on the most stable frame of random points using the Delaunay triangulation algorithm to obtain a plurality of new triangles; According to the multiple new triangles, multiple candidate fragmentation points are obtained; An MDH parameterized model of the crusher is established, evaluation indicators of the candidate crushing points are obtained based on the candidate crushing points, and an optimal crushing point is obtained according to the evaluation indicators of the candidate crushing points.

4. The method for selecting ore crushing points according to claim 3, characterized in that: The evaluation index calculation formula of the candidate breakpoint is as follows: R=a×Ab×d (1) Among them: a and b are empirical coefficients, A is the area of ​​the region where the breakup point is located, and d is the distance from the normal vector of the breakup point to the centroid of the point cloud.

5. A device for selecting ore crushing points, characterized in that: include: A target point cloud acquisition module is used to obtain the final target point cloud data of the ore based on the image data and the point cloud data using the yolov8 target detection model; The crushing point acquisition module is used to obtain the final crushing point data of the ore based on the final ore target point cloud data using the Delaunay triangulation algorithm.

6. The ore crushing point selection device according to claim 5, characterized in that: The target point cloud acquisition module is also used for: Based on the image data, the yolov8 target detection model is used to perform target recognition and instance segmentation, and all pixel points on the instance segmentation object contour within the yolo prediction box with a side length greater than a certain length are obtained; Calculating the two-dimensional convex hull corresponding to all pixel points on the contours of the multiple instance segmentation objects; After accumulating 50 frames of the point cloud data, project them onto a two-dimensional convex hull formed by all pixel points on the contours of the multiple instance segmentation objects and extract the point cloud data projected within the multiple two-dimensional convex hulls; The plurality of point cloud data extracted above are subjected to point cloud denoising, downsampling, dbscan clustering processing and 3D bounding box generation respectively to obtain a 3D bounding box whose length, width and height are greater than a certain threshold; Projecting eight vertices on the 3D bounding boxes of the plurality of clustering results that meet the conditions onto the image to form 2D bounding boxes, and calculating a plurality of intersection-over-union ratios of the plurality of 2D bounding boxes and the prediction boxes of the corresponding instance segmentation objects; Obtaining a maximum intersection-and-union ratio according to the plurality of intersection-and-union ratios, and obtaining corresponding target point cloud data according to the maximum intersection-and-union ratio; According to the target point cloud data, it is determined whether the distance between each point of the target point cloud data and the centroid of the target point cloud is greater than a distance threshold to delete outliers and obtain final target point cloud data.

7. The ore crushing point selection device according to claim 5, characterized in that: The breaking point acquisition module is also used for: Based on the final ore target point cloud data, multiple three-dimensional convex hulls of the point cloud data of multiple large-size ores are calculated respectively, the polygons on the multiple three-dimensional convex hulls are decomposed into multiple triangles, a certain number of random points are generated inside each triangle according to the area size, and only the random points located above the centroid of the target point cloud are retained; Downsampling and homogenizing the random points corresponding to the plurality of large-sized ores to obtain the homogenized random points corresponding to the plurality of large-sized ores; Accumulate 10 frames of homogenized random points corresponding to the plurality of large-size ores, and perform ICP registration on the random points of each frame of the 10 frames of random points and the random points of the previous and next frames, and perform Delaunay triangulation on the most stable frame of random points using the Delaunay triangulation algorithm to obtain a plurality of new triangles; According to the multiple new triangles, multiple candidate fragmentation points are obtained; An MDH parameterized model of the crusher is established, evaluation indicators of the candidate crushing points are obtained based on the candidate crushing points, and an optimal crushing point is obtained according to the evaluation indicators of the candidate crushing points.

8. A terminal, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the ore crushing point selection method described in any one of claims 1 to 4.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the storage medium is located is controlled to execute the ore crushing point selection method according to any one of claims 1 to 4.

10. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the method for selecting ore crushing points according to any one of claims 1 to 4.

Images