Coal quantity rapid analysis method, system, computer device and storage medium

Abstract

The present application belongs to the field of thermal power plants, and discloses a coal quantity rapid analysis method, system, computer equipment and storage medium, comprising: obtaining laser radar scanning point cloud data of a coal pile area; performing three-dimensional target detection on the laser radar scanning point cloud data of the coal pile area with the coal pile as a to-be-recognized target to obtain relative coordinates of a three-dimensional detection frame; obtaining laser radar scanning point cloud data within the three-dimensional detection frame according to the relative coordinates of the three-dimensional detection frame, and obtaining a pile shape type of the coal pile and relative size parameters of the coal pile according to the laser radar scanning point cloud data within the three-dimensional detection frame; and obtaining a volume of the coal pile according to the pile shape type of the coal pile, the relative coordinates of the three-dimensional detection frame and the relative size parameters of the coal pile. Compared with the existing manual coal piling method, the coal quantity rapid analysis method can realize real-time and rapid calculation of the volume of the coal pile based on the laser radar scanning point cloud data of the coal pile area, greatly reducing the time consumption of piling coal.

Description

Technical Field

[0001] This invention belongs to the field of thermal power plants, and in particular to a method, system, computer equipment and storage medium for rapid coal quantity analysis. Background Technology

[0002] Coal inventory is an important operational requirement for coal yard management in thermal power plants. Currently, the mainstream methods of coal inventory rely partly on manual inventory, which involves using a handheld laser coal inventory device to scan the coal pile to obtain its volume, or installing the laser coal inventory device on the guide rails of bucket wheel excavators, drones, or dry coal sheds to achieve automated coal inventory.

[0003] However, this manual coal inventory method requires a complete scan of the coal pile from multiple angles and three-dimensional reconstruction. Although the measurement accuracy is high, each measurement takes a long time, making it difficult to meet the demand for real-time and rapid coal inventory. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the existing coal inventory methods, which require multi-angle complete scanning of the coal pile and three-dimensional reconstruction, resulting in long measurement time and difficulty in meeting the real-time and rapid coal inventory requirements. This invention provides a method, system, computer equipment, and storage medium for rapid coal quantity analysis.

[0005] To achieve the above objectives, the present invention employs the following technical solution:

[0006] In a first aspect, the present invention provides a method for rapid analysis of coal quantity, comprising:

[0007] Acquire lidar scan point cloud data of the coal pile area;

[0008] Using a coal pile as the target to be identified, three-dimensional target detection is performed on the lidar scanning point cloud data of the coal pile area to obtain the relative coordinates of the three-dimensional detection box;

[0009] Based on the relative coordinates of the 3D detection frame, obtain the LiDAR scanning point cloud data within the 3D detection frame, and obtain the coal pile shape type and relative size parameters of the coal pile based on the LiDAR scanning point cloud data within the 3D detection frame.

[0010] The volume of the coal pile is obtained based on the pile shape type, the relative coordinates of the three-dimensional detection frame, and the relative size parameters of the coal pile.

[0011] Optionally, acquiring the lidar scan point cloud data of the coal pile area includes:

[0012] The lidar scanning point cloud data of the coal pile area is obtained by a lidar set up on one side of the coal pile.

[0013] The lidar has a detection range of not less than 100 meters, an angular resolution of not more than 0.05°, and a ranging resolution of not more than 10 mm.

[0014] Optionally, the three-dimensional target detection of the lidar scanning point cloud data of the coal pile area, with the coal pile as the target to be identified, includes:

[0015] Using coal piles as the target to be identified, the PointPillars laser point cloud 3D target detection algorithm, STD target detection algorithm, 3D SSD target detection algorithm, or CLOCs laser point cloud 3D target detection algorithm are used to perform three-dimensional target detection on the lidar scanning point cloud data of the coal pile area.

[0016] Optionally, obtaining the coal pile shape type and relative size parameters of the coal pile based on the lidar scan point cloud data within the three-dimensional detection frame includes:

[0017] The LiDAR scan point cloud data within the 3D detection frame is voxelized at multiple scales, and the number of LiDAR scan point clouds in each grid is recorded at different scales to obtain multi-scale voxelization information.

[0018] By inputting multi-scale voxelized information into a pre-defined deep neural network model for coal pile analysis, the pile shape type and relative size parameters of the coal pile are obtained.

[0019] Optionally, the deep neural network model for coal pile analysis is constructed in the following manner:

[0020] The preset stacking types are parametrically traversed, and for each set of parameters traversed, voxel grid data at different scales are generated to obtain training data.

[0021] A deep neural network model was constructed with multi-scale voxelized information as input and the coal pile shape type and relative size parameters as output. The deep neural network model was trained with training data to obtain a deep neural network model for coal pile analysis.

[0022] Optionally, the plurality of stacking types include one or more of the following: prism, frustum, pyramid, cone, truncated cone, elliptic frustum, semi-elliptic cylinder, and elliptic cone.

[0023] In a second aspect, the present invention provides a rapid coal quantity analysis system, comprising:

[0024] The data acquisition module is used to acquire lidar scan point cloud data of the coal pile area;

[0025] The target detection module is used to perform three-dimensional target detection on the lidar scanning point cloud data of the coal pile area with the coal pile as the target to be identified, and to obtain the relative coordinates of the three-dimensional detection box;

[0026] The coal pile analysis module is used to obtain the LiDAR scan point cloud data within the 3D detection frame based on the relative coordinates of the 3D detection frame, and to obtain the coal pile shape type and relative size parameters of the coal pile based on the LiDAR scan point cloud data within the 3D detection frame.

[0027] The volume calculation module is used to obtain the volume of the coal pile based on the pile shape type, the relative coordinates of the 3D detection frame, and the relative size parameters of the coal pile.

[0028] Optionally, obtaining the coal pile shape type and relative size parameters of the coal pile based on the lidar scan point cloud data within the three-dimensional detection frame includes:

[0029] The LiDAR scan point cloud data within the 3D detection frame is voxelized at multiple scales, and the number of LiDAR scan point clouds in each grid is recorded at different scales to obtain multi-scale voxelization information.

[0030] By inputting multi-scale voxelized information into a pre-defined deep neural network model for coal pile analysis, the pile shape type and relative size parameters of the coal pile are obtained.

[0031] In a third aspect, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described rapid coal quantity analysis method.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described rapid coal quantity analysis method.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] This invention provides a rapid coal quantity analysis method. First, it acquires lidar scan point cloud data of the coal pile area. Then, based on this data, it performs 3D target detection on the coal pile as the target, obtaining the relative coordinates of the 3D detection frame to determine the location and spatial range of the coal pile area. Next, it acquires lidar scan point cloud data within the 3D detection frame, and based on this, determines the pile shape type and relative size parameters of the coal pile. Finally, the coal pile volume can be obtained from the pile shape type, the relative coordinates of the 3D detection frame, and the relative size parameters of the coal pile, enabling real-time and rapid coal quantity estimation and analysis. Compared to existing manual coal inventory methods, this rapid coal quantity analysis method achieves real-time and rapid calculation of the coal pile volume based on lidar scan point cloud data of the coal pile area, significantly reducing the time required for coal inventory. Attached Figure Description

[0035] Figure 1 This is a flowchart of the rapid coal quantity analysis method according to an embodiment of the present invention.

[0036] Figure 2 This is a structural block diagram of the rapid coal quantity analysis system according to an embodiment of the present invention. Detailed Implementation

[0037] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0039] The present invention will now be described in further detail with reference to the accompanying drawings:

[0040] See Figure 1 In one embodiment of the present invention, a method for rapid coal quantity analysis is provided, which can accurately and quickly determine the volume of coal piles and meet the needs of real-time and rapid coal inventory.

[0041] Specifically, this rapid coal quantity analysis method includes the following steps:

[0042] S1: Acquire lidar scan point cloud data of the coal pile area.

[0043] S2: Using the coal pile as the target to be identified, perform 3D target detection on the lidar scanning point cloud data of the coal pile area to obtain the relative coordinates of the 3D detection box.

[0044] S3: Based on the relative coordinates of the 3D detection frame, obtain the LiDAR scanning point cloud data within the 3D detection frame, and obtain the pile shape type and relative size parameters of the coal pile based on the LiDAR scanning point cloud data within the 3D detection frame.

[0045] S4: The volume of the coal pile is obtained based on the pile shape type, the relative coordinates of the three-dimensional detection frame, and the relative size parameters of the coal pile.

[0046] In summary, the rapid coal quantity analysis method of this invention first acquires lidar scan point cloud data of the coal pile area. Then, based on this data, it performs 3D target detection on the coal pile as the target to be identified, obtaining the relative coordinates of the 3D detection frame to determine the location and spatial range of the coal pile area. Next, it acquires lidar scan point cloud data within the 3D detection frame, and based on this, determines the pile shape type and relative size parameters of the coal pile. Finally, the coal pile volume can be obtained from the pile shape type, the relative coordinates of the 3D detection frame, and the relative size parameters of the coal pile, enabling real-time and rapid coal quantity estimation and analysis. Compared to existing manual coal inventory methods, this rapid coal quantity analysis method can achieve real-time and rapid calculation of the coal pile volume based on lidar scan point cloud data of the coal pile area, greatly reducing the time spent on coal inventory.

[0047] Among them, the relative size parameter, also known as the normalized value of the key parameter, refers to the ratio of key parameters of the target point cloud object corresponding to the stack shape type.

[0048] For example, given point cloud data of a coal pile, and the relative coordinates of its corresponding 3D detection frame, such as the height H and width W of the detection frame, matching the pile shape type of the target point cloud data reveals it to be a cone. This cone also has a rectangular / hexahedral envelope similar to the 3D detection frame, with a height h and width w. The cone's base (ellipse) has major axis a, minor axis b, eccentric position x and y at the cone's vertex, and a height l. Assuming the envelope height h = 1, the remaining relative size parameters are: w = 1.2, a = 0.6, b = 0.4, x = 0.1, y = -0.05, and l = 1. Finally, the actual size parameters of the cone need to be determined based on the relationship between the 3D detection frame and the relative size parameters of the point cloud data. Assuming the 3D detection frame is calculated to be H = 5m and W = 6m using point cloud coordinates, then the envelope is h = H = 5m and w = W = 6m. The actual dimensions of the cone are a = 3m, b = 2m, x = 0.5m, y = -0.25m, and l = 5m. Finally, the volume of the cone is calculated using the volume formula V = 1 / 3 * pi * a * b * l, thus the volume of the coal pile corresponding to the target point cloud can be obtained.

[0049] In one possible implementation, acquiring the lidar scan point cloud data of the coal pile area includes: acquiring the lidar scan point cloud data of the coal pile area using a lidar installed on one side of the coal pile.

[0050] The lidar has a detection range of not less than 100 meters, an angular resolution of not more than 0.05°, and a ranging resolution of not more than 10 mm.

[0051] Specifically, the placement of the lidar should ensure that the coal pile to be inspected is completely within its scanning range, and it can be placed at multiple angles near the coal pile to ensure the accuracy of the final results.

[0052] In one possible implementation, the three-dimensional target detection of the lidar scanning point cloud data of the coal pile area with the coal pile as the target to be identified includes: using the coal pile as the target to be identified, the PointPillars lidar point cloud 3D target detection algorithm, the STD target detection algorithm, the 3D SSD target detection algorithm, or the CLOCs lidar point cloud 3D target detection algorithm to perform three-dimensional target detection on the lidar scanning point cloud data of the coal pile area.

[0053] Specifically, this embodiment uses the PointPillars laser point cloud 3D target detection algorithm as an example.

[0054] The acquired LiDAR scan point cloud data is divided into P cells on the XY plane. For the point cloud within each cell, its information is encoded into a 9-dimensional vector D(x, y, z, xc, yc, zc, xp, yp). Here, x, y, z, and r represent the three coordinate components of the point cloud and the reflection intensity, respectively; xc, yc, and zc are the offsets of the point cloud coordinates from the average position of all point clouds within the cell; and xp and yp are the offsets of the point cloud coordinates from the center position of the cell. For each unit, if the number of point clouds is greater than N, N point clouds are randomly retained; if the number of point clouds is less than N, zeros are padded to N point clouds. The processed point clouds are then encoded into tensors of dimension (D, P, N). These (D, P, N) tensors are mapped to tensors of dimension (C, W, H) using a fully connected network. A convolutional neural network is then applied to the obtained (C, W, H) tensors to output a 3D bounding box for the coal pile, represented by a 7-dimensional vector O(X, Y, Z, L, W, H, theta). Here, X, Y, and Z are the center coordinates of the 3D bounding box, L, W, and H are the length, width, and height of the 3D bounding box, and theta is the orientation angle of the 3D bounding box.

[0055] In one possible implementation, obtaining the coal pile shape type and relative size parameters of the coal pile based on the lidar scan point cloud data within the three-dimensional detection frame includes: performing multi-scale voxelization on the lidar scan point cloud data within the three-dimensional detection frame, and recording the number of lidar scan point clouds in each grid at different scales to obtain multi-scale voxelization information; inputting the multi-scale voxelization information into a preset deep neural network model for coal pile analysis to obtain the coal pile shape type and relative size parameters of the coal pile.

[0056] Voxelization is a method of representing objects using the most basic geometric form. The multi-scale voxelization process includes: using squares as voxel units, first using the largest scale, i.e., a 4*4 voxel grid, to obtain the voxelization result of the target point cloud. At this time, the coordinates of the center points of all voxels containing point cloud data and the voxel lengths (xi,yi,ai,bi) are recorded. Then, voxelization is performed at smaller scales to obtain more detailed results, such as an 8*8 voxel network, and the coordinates of the center points of all voxels containing point cloud data and the voxel lengths are recorded. Then, voxelization is performed at even smaller scales, such as 16*16, 32*32, etc., and the voxelization results at each scale are saved. Finally, the voxelization results at each scale are summarized and processed to obtain the multi-scale voxelization result.

[0057] The deep neural network model for coal pile analysis is constructed as follows: several preset pile shapes are parametrically traversed, and for each set of parameters traversed, voxel grid data at different scales are generated to obtain training data; a deep neural network model is built with multi-scale voxelized information as input and the pile shape type and relative size parameters of the coal pile as output; the deep neural network model is trained with the training data to obtain the deep neural network model for coal pile analysis.

[0058] The specific process of parametrically traversing several preset stacking types and generating voxel mesh data at different scales for each parameter combination encountered includes: First, classifying the stacking types. Second, identifying the control parameters for each stacking type; for example, a frustum has side length, height, base angle, and hypotenuse angle. Then, counting the number N independent control parameters for the frustum stacking type and determining their value ranges, and performing dimensionless or normalized transformations on these N independent control parameters. Finally, obtaining the combination of each set of independent control parameters: for example, if the ground angle θ1 ranges from (10, 170) and the height Z1 ranges from (0.1, 2.0), then taking values ​​for θ1 every 1° and for Z1 every 0.01, a 2D array (θi, Zi) is obtained. After obtaining such an N-dimensional array, we obtain m1*m2*……mN parameter combinations. The program generates point cloud data for the frustum surface under the control of each parameter combination, performs multi-scale voxelization on the point cloud data, and generates voxel mesh data at different scales.

[0059] The aforementioned pile shapes include one or more of the following: prism, frustum, pyramid, cone, truncated cone, elliptic frustum, semi-elliptic cylinder, and elliptic cone. These encompass basic geometric shapes similar to common coal pile shapes.

[0060] The following are embodiments of the apparatus of the present invention, which can be used to execute embodiments of the method of the present invention. For details not disclosed in the apparatus embodiments, please refer to the embodiments of the method of the present invention.

[0061] See Figure 2 In another embodiment of the present invention, a rapid coal quantity analysis system is provided, which can be used to implement the above-mentioned rapid coal quantity analysis method. Specifically, the rapid coal quantity analysis system includes a data acquisition module, a target detection module, a coal pile analysis module, and a volume calculation module.

[0062] The system comprises the following modules: a data acquisition module for acquiring lidar scan point cloud data of the coal pile area; a target detection module for performing 3D target detection on the lidar scan point cloud data of the coal pile area to obtain the relative coordinates of the 3D detection frame; a coal pile analysis module for acquiring lidar scan point cloud data within the 3D detection frame based on the relative coordinates of the 3D detection frame, and obtaining the pile shape type and relative size parameters of the coal pile based on the lidar scan point cloud data within the 3D detection frame; and a volume calculation module for obtaining the coal pile volume based on the pile shape type, the relative coordinates of the 3D detection frame, and the relative size parameters of the coal pile.

[0063] In one possible implementation, acquiring the lidar scanning point cloud data of the coal pile area includes: acquiring the lidar scanning point cloud data of the coal pile area using a lidar installed on one side of the coal pile; wherein the lidar has a detection range of not less than 100 meters, an angular resolution of not more than 0.05°, and a ranging resolution of not more than 10 mm.

[0064] In one possible implementation, the three-dimensional target detection of the lidar scanning point cloud data of the coal pile area with the coal pile as the target to be identified includes: using the coal pile as the target to be identified, the PointPillars lidar point cloud 3D target detection algorithm, the STD target detection algorithm, the 3D SSD target detection algorithm, or the CLOCs lidar point cloud 3D target detection algorithm to perform three-dimensional target detection on the lidar scanning point cloud data of the coal pile area.

[0065] In one possible implementation, obtaining the coal pile shape type and relative size parameters of the coal pile based on the lidar scan point cloud data within the three-dimensional detection frame includes: performing multi-scale voxelization on the lidar scan point cloud data within the three-dimensional detection frame, and recording the number of lidar scan point clouds in each grid at different scales to obtain multi-scale voxelization information; inputting the multi-scale voxelization information into a preset deep neural network model for coal pile analysis to obtain the coal pile shape type and relative size parameters of the coal pile.

[0066] In one possible implementation, the deep neural network model for coal pile analysis is constructed as follows: several preset pile shapes are parametrically traversed, and for each set of parameters traversed, voxel grid data at different scales are generated to obtain training data; a deep neural network model is built with multi-scale voxelized information as input and the pile shape type and relative size parameters of the coal pile as output; the deep neural network model is trained with the training data to obtain the deep neural network model for coal pile analysis.

[0067] In one possible implementation, the plurality of stack types include one or more of the following: prism, frustum, pyramid, cone, truncated cone, elliptic frustum, semi-elliptic cylinder, and elliptic cone.

[0068] All relevant content of each step involved in the aforementioned embodiments of the rapid coal quantity analysis method can be referred to the functional description of the corresponding functional module of the rapid coal quantity analysis system in this invention, and will not be repeated here.

[0069] The module division in this embodiment of the invention is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of the invention can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0070] In another embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used for the operation of a rapid coal quantity analysis method.

[0071] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the rapid coal quantity analysis method in the above embodiments.

[0072] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0073] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0074] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0075] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A rapid coal quantity analysis method, characterized in that, include: Acquire lidar scan point cloud data of the coal pile area; Using a coal pile as the target to be identified, three-dimensional target detection is performed on the lidar scanning point cloud data of the coal pile area to obtain the relative coordinates of the three-dimensional detection box; Based on the relative coordinates of the 3D detection frame, the LiDAR scanning point cloud data within the 3D detection frame is obtained. The LiDAR scanning point cloud data within the 3D detection frame is then voxelized at multiple scales, and the number of LiDAR scanning point clouds in each grid is recorded at different scales to obtain multi-scale voxelization information. The multi-scale voxelization information is then input into a preset deep neural network model for coal pile analysis to obtain the coal pile shape type and the relative size parameters of the coal pile. The volume of the coal pile is obtained based on the pile shape type, the relative coordinates of the three-dimensional detection frame, and the relative size parameters of the coal pile.

2. The rapid coal quantity analysis method according to claim 1, characterized in that, The acquisition of lidar scanning point cloud data of the coal pile area includes: The lidar scanning point cloud data of the coal pile area is obtained by a lidar set up on one side of the coal pile. The lidar has a detection range of not less than 100 meters, an angular resolution of not more than 0.05°, and a ranging resolution of not more than 10 mm.

3. The rapid coal quantity analysis method according to claim 1, characterized in that, The three-dimensional target detection of the LiDAR scanning point cloud data of the coal pile area, with the coal pile as the target to be identified, includes: Using coal piles as the target to be identified, the PointPillars laser point cloud 3D target detection algorithm, STD target detection algorithm, 3D SSD target detection algorithm, or CLOCs laser point cloud 3D target detection algorithm are used to perform three-dimensional target detection on the lidar scanning point cloud data of the coal pile area.

4. The rapid coal quantity analysis method according to claim 1, characterized in that, The deep neural network model for coal pile analysis is constructed in the following manner: The preset stacking types are parametrically traversed, and for each set of parameters traversed, voxel grid data at different scales are generated to obtain training data. A deep neural network model was constructed with multi-scale voxelized information as input and the coal pile shape type and relative size parameters as output. The deep neural network model was trained with training data to obtain a deep neural network model for coal pile analysis.

5. The rapid coal quantity analysis method according to claim 4, characterized in that, The aforementioned pile shapes include one or more of the following: prism, frustum, pyramid, cone, truncated cone, elliptic frustum, semi-elliptic cylinder, and elliptic cone.

6. A rapid coal quantity analysis system, characterized in that, include: The data acquisition module is used to acquire lidar scan point cloud data of the coal pile area; The target detection module is used to perform three-dimensional target detection on the lidar scanning point cloud data of the coal pile area with the coal pile as the target to be identified, and to obtain the relative coordinates of the three-dimensional detection box; The coal pile analysis module is used to acquire the LiDAR scan point cloud data within the 3D detection frame based on the relative coordinates of the 3D detection frame, perform multi-scale voxelization on the LiDAR scan point cloud data within the 3D detection frame, and record the number of LiDAR scan point clouds in each grid at different scales to obtain multi-scale voxelization information; the multi-scale voxelization information is input into the preset coal pile analysis deep neural network model to obtain the coal pile shape type and the relative size parameters of the coal pile; The volume calculation module is used to obtain the volume of the coal pile based on the pile shape type, the relative coordinates of the 3D detection frame, and the relative size parameters of the coal pile.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the rapid coal quantity analysis method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the rapid coal quantity analysis method as described in any one of claims 1 to 5.

Images