An unmanned aerial vehicle based laser disc coal system

Abstract

This invention relates to the field of coal pile detection technology, specifically disclosing a laser coal inventory system based on a drone. The method includes a coal pile range determination module, used to acquire a blurred image of the coal pile containing image parameters using a preset fixed camera, analyze the blurred image, and determine the range of the coal pile; a top-view image acquisition module, used to determine a detection path based on the coal pile range, and acquire a top-view image of the coal pile containing its location and time based on the detection path; an inspection path determination module, used to identify the top-view image, determine the coal pile distribution information, and determine the drone's inspection path based on the coal pile distribution information; and a 3D coal pile creation module, used to send the inspection path to the drone, receive point cloud data fed back by the drone, and create a 3D coal pile based on the point cloud data. This invention allows the drone to autonomously complete the coal inventory process, enabling the drone to perform coal inventory at high altitudes with high accuracy, flexibility, and intelligence.

Description

Technical Field

[0001] This invention relates to the field of coal pile detection technology, specifically a laser coal inventory system based on unmanned aerial vehicles (UAVs). Background Technology

[0002] "Coal inventory" refers to the process of scanning and measuring coal piles using methods such as drones to obtain information about their shape, volume, and weight. This process is commonly used in coal mines and coal yards to help better manage and optimize coal storage, transportation, and use by accurately measuring coal pile data. In drone-based laser coal inventory, LiDAR technology is typically used in conjunction with the drone for measurement. However, because LiDAR itself consumes a lot of energy, when mounted on a drone, it significantly shortens the drone's flight time, limiting the area it can cover in a single operation and making it impossible to efficiently complete large-area coal inventory work. Therefore, how to improve the drone's flight time is the technical problem that this invention aims to solve. Summary of the Invention

[0003] The purpose of this invention is to provide a laser coal inventory system based on unmanned aerial vehicles (UAVs) to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] A drone-based laser coal counting system, the system comprising:

[0006] The coal pile range determination module is used to acquire a blurred image of the coal pile containing image parameters based on a preset fixed camera, analyze the blurred image, and determine the range of the coal pile.

[0007] The top-view image acquisition module is used to determine the detection path based on the range of the coal pile, and acquire a top-view image of the coal pile containing its location and time according to the detection path;

[0008] The inspection path determination module is used to identify the top-view image, determine the coal pile distribution information, and determine the inspection path of the UAV based on the coal pile distribution information; wherein, the height of the inspection path is less than the height of the detection path.

[0009] The 3D coal pile creation module is used to send the inspection path to the drone, receive the point cloud data fed back by the drone, and create a 3D coal pile based on the point cloud data.

[0010] The display module is used to display the created 3D coal pile.

[0011] As a further aspect of the present invention, the coal pile range determination module includes:

[0012] The instruction sending unit is used to query the preset fixed camera and send a shooting instruction to the fixed camera;

[0013] A blurred image receiving unit is used to receive images fed back from a fixed camera as blurred images.

[0014] The parameter receiving unit is used to receive image parameters when the fixed camera acquires a blurred image, the image parameters including the image acquisition direction and acquisition wide angle;

[0015] The image analysis unit is used to analyze blurry images and determine the extent of the coal pile.

[0016] As a further aspect of the present invention, the analysis of the blurred image to determine the range of the coal pile includes:

[0017] Locating the boundary line of a coal pile in a blurred image based on the color value of the coal pile;

[0018] The coal pile boundary line is mapped onto the horizontal plane based on the image parameters to obtain the horizontal mapping line;

[0019] By statistically analyzing the horizontal mapping lines corresponding to the boundary lines of all coal piles, the planar profile can be obtained.

[0020] The planar outline is expanded according to a preset ratio, and the expanded planar outline is used as the range of the coal pile.

[0021] As a further embodiment of the present invention, the top-view image acquisition module includes:

[0022] The maximum altitude determination unit is used to query the image acquisition accuracy of the UAV and determine the maximum altitude based on the image acquisition accuracy and the detection range at different altitudes.

[0023] The path creation unit is used to create a detection path based on the maximum altitude; the sum of the image acquisition range of the UAV on the detection path is greater than the range of the coal pile.

[0024] The top-view image receiving unit is used to send the detection path to the UAV and receive the top-view image containing position and time from the UAV.

[0025] As a further embodiment of the present invention, the inspection path determination module includes:

[0026] The stitching unit is used to acquire the most recent images at each location and stitch them together according to their positional relationships to obtain the overall image.

[0027] The contour recognition unit is used to locate the boundary line of the coal pile in a blurred image based on the color value of the coal pile, and obtain the contour of the coal pile.

[0028] The contour application unit is used to determine the inspection path of the UAV based on the obtained coal pile contour.

[0029] As a further aspect of the present invention, the step of determining the inspection path of the UAV based on the obtained coal pile outline includes:

[0030] To query the detection altitude range of the laser device built into the drone;

[0031] Select the minimum height within the detection height range to obtain the single detection area of ​​the UAV at the minimum height;

[0032] The coal pile outline is divided into several strip areas based on a single detection area in a preset direction;

[0033] Select the center line of the strip area as the inspection path.

[0034] As a further embodiment of the present invention, the three-dimensional coal pile creation module includes:

[0035] The point cloud data receiving unit is used to send the inspection path to the drone and receive the point cloud data fed back by the drone.

[0036] A 3D coal pile creation unit is used to create a 3D coal pile based on the point cloud data and the identified coal pile outline.

[0037] The point cloud data is obtained by a lidar mounted on the UAV.

[0038] As a further aspect of the present invention, the three-dimensional coal pile creation module further includes:

[0039] The point cloud data recording unit is used to record the point cloud data acquired by all drones at various locations when the number of drones is not unique.

[0040] The difference calculation unit is used to compare the point cloud data acquired by all drones at the same location and calculate the difference.

[0041] A probability determination unit is used to determine the sampling probability of each location based on the difference degree; the sampling probability is directly proportional to the difference degree.

[0042] The decision unit is used to determine whether to acquire point cloud data for any UAV when it moves to a certain position, based on the acquisition probability.

[0043] As a further embodiment of the present invention, the three-dimensional coal pile creation module further includes: the display module includes:

[0044] The statistical unit is used to acquire and statistically analyze the three-dimensional coal pile at different times within a preset time period;

[0045] The duration determination unit is used to receive the display cycle set by the administrator, calculate the ratio of the time cycle to the display cycle, and determine the display duration of the three-dimensional coal pile at each moment;

[0046] The display execution unit is used to cyclically display the three-dimensional coal pile.

[0047] As a further aspect of the present invention, the UAV has a built-in obstacle avoidance module. When an obstacle avoidance action occurs, it records the obstacle avoidance location and generates an information acquisition interruption signal. After the obstacle avoidance is completed, it returns to the obstacle avoidance location and ends the information acquisition interruption signal.

[0048] Compared with the prior art, the beneficial effects of the present invention are:

[0049] The technical solution of this invention provides an image-based pre-judgment process, which reduces the application time and frequency of lidar, greatly reduces energy consumption, and improves the endurance of UAVs. In addition, the coal inventory process is completed autonomously by the UAV, which can perform coal inventory at high altitudes with high precision, high flexibility, and high level of intelligence. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention.

[0051] Figure 1 This is a schematic diagram of a drone-based laser coal sorting system. Detailed Implementation

[0052] To make the technical problems to be solved, the technical solutions, and the beneficial effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0053] Figure 1 This is a schematic diagram of a drone-based laser coal reconciliation system. In this embodiment of the invention, a drone-based laser coal reconciliation system 10 includes:

[0054] The coal pile range determination module 11 is used to acquire a blurred image of the coal pile containing image parameters based on a preset fixed camera, analyze the blurred image, and determine the range of the coal pile.

[0055] The top-view image acquisition module 12 is used to determine the detection path based on the range of the coal pile, and acquire a top-view image of the coal pile containing the location and time according to the detection path;

[0056] The inspection path determination module 13 is used to identify the top view image, determine the coal pile distribution information, and determine the inspection path of the UAV based on the coal pile distribution information; wherein, the height of the inspection path is less than the height of the detection path.

[0057] The 3D coal pile creation module 14 is used to send the inspection path to the UAV, receive the point cloud data fed back by the UAV, and create a 3D coal pile based on the point cloud data.

[0058] Display module 15 is used to display the created 3D coal pile.

[0059] The technical solution of this invention is applied to coal inventory scenarios. "Coal inventory" refers to the process of scanning and measuring coal piles using certain means (such as drones) to obtain information such as the shape, volume, and weight of the coal piles. This process is commonly used in coal mines and coal yards to help better manage and optimize the storage, transportation, and use of coal by accurately measuring coal pile data.

[0060] In a scene where coal is placed, multiple fixed cameras are usually set up to acquire real-time information about the coal's condition. Their accuracy is generally low, and they are mainly used to monitor for the presence of unauthorized personnel. The images of the coal piles acquired by the fixed cameras are called blurry images because of their low accuracy. By analyzing the blurry images, the approximate location of the coal pile can be determined, which is called the coal pile range. The coal pile range is a two-dimensional area.

[0061] The detection path is determined based on the range of the coal pile. Since the range of the coal pile is an approximate area, the detection path is also an approximate path. The UAV moves along the detection path and continuously acquires top-view images of the coal pile. When acquiring top-view images, the position and time are recorded. At this time, the top-view images have higher accuracy compared to blurry images.

[0062] By identifying the high-precision top-view image, the distribution of coal piles can be obtained, which is called coal pile distribution information. The final inspection path is determined based on the coal pile distribution information. At this time, the inspection path has a very high degree of fit with the actual situation, and there are almost no invalid detections.

[0063] The inspection path is sent to the drone, and the point cloud data fed back by the drone is received. A three-dimensional coal pile is created based on the point cloud data. The advantage of the three-dimensional coal pile is its intuitiveness. The creation of the three-dimensional coal pile can be displayed so that the managers can intuitively view the status of the coal pile.

[0064] Specifically, this application typically involves multiple drones. For multi-drone operation scenarios, a specialized data synthesis algorithm and technical process are researched and developed. This technology can accurately register, fuse, and optimize point cloud data acquired by lidar from different drones, eliminating data deviations caused by differences in drone flight attitude and data acquisition time. Ultimately, it forms a complete, high-precision 3D point cloud data model of the coal yard, providing a reliable data foundation for accurate coal inventory. This process falls under the category of drone-based point cloud data acquisition solutions.

[0065] Regarding point cloud data, the drone is equipped with a lidar sensor and flies over or around the coal pile to scan the surface of the coal pile with radar. The lidar emits a laser beam and receives the reflected signal to accurately measure the position and distance of each point. During the flight, the lidar sensor continuously scans the surface of the coal pile to acquire a large amount of point cloud data (i.e., three-dimensional coordinate points obtained through laser ranging). This point cloud data can reflect the shape, surface unevenness and other characteristics of the coal pile.

[0066] In a preferred embodiment of the technical solution of the present invention, the coal pile range determination module 11 includes:

[0067] The instruction sending unit is used to query the preset fixed camera and send a shooting instruction to the fixed camera;

[0068] A blurred image receiving unit is used to receive images fed back from a fixed camera as blurred images.

[0069] The parameter receiving unit is used to receive image parameters when the fixed camera acquires a blurred image, the image parameters including the image acquisition direction and acquisition wide angle;

[0070] The image analysis unit is used to analyze blurry images and determine the extent of the coal pile.

[0071] The above describes the functions of the fixed camera: querying the location of the fixed camera, sending a shooting command to the fixed camera, and after the fixed camera captures an image, it sends it back to the central terminal. The image is not very accurate, so it is called a blurry image. At the same time, when the fixed camera acquires the image, it also needs to acquire image parameters, including the image acquisition direction and acquisition wide angle. After receiving the blurry image, the central terminal analyzes the blurry image to determine the range of the coal pile.

[0072] Specifically, the analysis of the blurred image to determine the extent of the coal pile includes:

[0073] Locating the boundary line of a coal pile in a blurred image based on the color value of the coal pile;

[0074] The coal pile boundary line is mapped onto the horizontal plane based on the image parameters to obtain the horizontal mapping line;

[0075] By statistically analyzing the horizontal mapping lines corresponding to the boundary lines of all coal piles, the planar profile can be obtained.

[0076] The planar outline is expanded according to a preset ratio, and the expanded planar outline is used as the range of the coal pile.

[0077] The color value of the coal pile is known data, generally black or grayish-black. The color value of the coal pile is a range of color values. Based on the color value of the coal pile, the boundary line of the coal pile is located in the blurred image (contour recognition). Since the acquisition position and acquisition angle of each image are different, it is not necessarily an image from a top view. Therefore, it is necessary to perform a transformation. Based on the known acquisition position and acquisition direction, mapping the image to the horizontal plane is not complicated, and the mapping process is existing technology. Specifically, the boundary line of the coal pile is located in the blurred image based on the color value of the coal pile. According to the image parameters, the boundary line of the coal pile is mapped to the horizontal plane to obtain the horizontal mapping line. The horizontal mapping lines corresponding to all the boundary lines of the coal pile are counted to obtain the planar contour.

[0078] In the technical solution of this invention, the desired coal pile range is an approximate range, which should be as large as possible and may include the actual coal body. Therefore, the above also introduces an expansion scheme to expand the planar outline to obtain the final coal pile range.

[0079] As a preferred embodiment of the technical solution of the present invention, the top view image acquisition module 12 includes:

[0080] The maximum altitude determination unit is used to query the image acquisition accuracy of the UAV and determine the maximum altitude based on the image acquisition accuracy and the detection range at different altitudes.

[0081] The path creation unit is used to create a detection path based on the maximum altitude; the sum of the image acquisition range of the UAV on the detection path is greater than the range of the coal pile.

[0082] The top-view image receiving unit is used to send the detection path to the UAV and receive the top-view image containing position and time from the UAV.

[0083] The above describes the process of acquiring the top-down image. The image acquisition accuracy of the UAV is queried, and is expressed in pixels. The maximum height is determined based on the image acquisition accuracy and the detection range at different altitudes. Regarding the impact of altitude, the greater the altitude, the larger the detection range (a subset of the coal pile area) corresponding to the top-down image. The larger the actual range corresponding to one pixel, the lower the accuracy. The minimum accuracy entered by the administrator is queried to determine a maximum height. A detection path is created at the maximum altitude, and the detection path is sent to the UAV. The UAV then sends back a top-down image containing its position and time.

[0084] It should be noted that the area corresponding to the top-down view image collected by the drone along the detection path is larger than the actual coal pile area.

[0085] As a preferred embodiment of the technical solution of the present invention, the inspection path determination module 13 includes:

[0086] The stitching unit is used to acquire the most recent images at each location and stitch them together according to their positional relationships to obtain the overall image.

[0087] The contour recognition unit is used to locate the boundary line of the coal pile in a blurred image based on the color value of the coal pile, and obtain the contour of the coal pile.

[0088] The contour application unit is used to determine the inspection path of the UAV based on the obtained coal pile contour.

[0089] In one embodiment of the technical solution of this invention, the images of the most recent time at each location are acquired and stitched together according to their positional relationships to obtain an image of the entire coal pile, referred to as the overall image. Then, based on the color values ​​of the coal pile, the boundary line of the coal pile is located in the blurred image to obtain the coal pile outline, which is also a outline recognition process. Since the overall image has higher accuracy than the blurred image, the identified outline is also more accurate. Finally, the inspection path of the UAV is determined according to the obtained coal pile outline. When the UAV moves on the inspection path, the actual point cloud data is acquired using LiDAR.

[0090] Specifically, the process of determining the UAV inspection path based on the obtained coal pile outline includes:

[0091] To query the detection altitude range of the laser device built into the drone;

[0092] Select the minimum height within the detection height range to obtain the single detection area of ​​the UAV at the minimum height;

[0093] The coal pile outline is divided into several strip areas based on a single detection area in a preset direction;

[0094] Select the center line of the strip area as the inspection path.

[0095] In one example of the technical solution of this invention, the detection height range of the laser device built into the UAV is queried, the minimum height is selected within the detection height range, and the single detection area of ​​the UAV at the minimum height is obtained. The coal pile outline is divided into several strip areas based on the single detection area in a preset direction. The center line of the strip area is selected as the inspection path. This process is actually somewhat similar to the process of obtaining the detection path (used to obtain the top view image). The difference is that the single detection area in the process of determining the detection path is the single detection area at the maximum height.

[0096] The reason for selecting the minimum height within the detection height range is to obtain more refined point cloud data. Of course, if the cost is limited, the maximum height can also be selected within the detection height range. In this case, the accuracy of the point cloud data will decrease slightly, the single detection area will be larger, the number of strip areas will be smaller, and the total length of the inspection path will be smaller.

[0097] As a preferred embodiment of the technical solution of the present invention, the three-dimensional coal pile creation module 14 includes:

[0098] The point cloud data receiving unit is used to send the inspection path to the drone and receive the point cloud data fed back by the drone.

[0099] A 3D coal pile creation unit is used to create a 3D coal pile based on the point cloud data and the identified coal pile outline.

[0100] The point cloud data is obtained by a lidar mounted on the UAV.

[0101] In one example of the present invention, the specific process of acquiring and applying point cloud data is described. The inspection path is sent to the UAV, the point cloud data fed back by the UAV is received, and a three-dimensional coal pile is created based on the point cloud data and the identified coal pile outline. Specifically, the coal pile outline is equivalent to a two-dimensional range, and the point cloud data represents the height of each point within the two-dimensional range. By introducing height values ​​at each coordinate within the two-dimensional range based on the point cloud data, the actual dimension expansion can be achieved.

[0102] As a preferred embodiment of the technical solution of the present invention, the three-dimensional coal pile creation module 14 further includes:

[0103] The point cloud data recording unit is used to record the point cloud data acquired by all drones at various locations when the number of drones is not unique.

[0104] The difference calculation unit is used to compare the point cloud data acquired by all drones at the same location and calculate the difference.

[0105] A probability determination unit is used to determine the sampling probability of each location based on the difference degree; the sampling probability is directly proportional to the difference degree.

[0106] The decision unit is used to determine whether to acquire point cloud data for any UAV when it moves to a certain position, based on the acquisition probability.

[0107] The above simplifies the application process of LiDAR. When the number of drones is not unique, the point cloud data acquired by all drones at each location is recorded. The point cloud data acquired by all drones at the same location is compared, and the difference is calculated. The difference reflects the stability of the point cloud data at that location. The acquisition probability at each location is determined based on the difference. The smaller the difference, the higher the stability and the lower the acquisition probability. For any drone, when it moves to a certain location, it is determined whether to acquire point cloud data based on the acquisition probability. For example, when the acquisition probability is 30%, each drone has only a 30% probability of acquiring point cloud data at that location. If it does not acquire data, the latest existing data can be used. This process actually reduces the detection frequency of drones and improves endurance.

[0108] As a preferred embodiment of the technical solution of the present invention, the three-dimensional coal pile creation module further includes: the display module includes:

[0109] The statistical unit is used to acquire and statistically analyze the three-dimensional coal pile at different times within a preset time period;

[0110] The duration determination unit is used to receive the display cycle set by the administrator, calculate the ratio of the time cycle to the display cycle, and determine the display duration of the three-dimensional coal pile at each moment;

[0111] The display execution unit is used to cyclically display the three-dimensional coal pile.

[0112] In one example of the technical solution of the present invention, the three-dimensional display process is dynamically expanded. The time period is generally six hours and the display period is generally one minute. The three-dimensional coal pile at different times within the preset time period is acquired and statistically analyzed. The display period set by the administrator is received, the ratio of the time period to the display period is calculated, and the display duration of the three-dimensional coal pile at each time moment is determined, that is, how many milliseconds the three-dimensional coal pile is displayed at each time moment, so as to cyclically display the three-dimensional coal pile.

[0113] In layman's terms, it displays a 3D coal pile of six hours within one minute, which can be compared to a "fast forward" display function.

[0114] In a preferred embodiment of the technical solution of the present invention, the UAV has a built-in obstacle avoidance module. When an obstacle avoidance action occurs, it records the obstacle avoidance location and generates an information acquisition interruption signal. After obstacle avoidance is completed, it returns to the obstacle avoidance location and terminates the information acquisition interruption signal. The acquisition interruption signal is used to stop the information acquisition process, including the image acquisition process and the point cloud data acquisition process.

[0115] In one embodiment of the technical solution of this invention, a novel unmanned aerial vehicle (UAV) is employed. This UAV possesses strong autonomous flight capabilities and can automatically fly and operate within the coal yard area according to preset flight paths and mission instructions. Simultaneously, the UAV is equipped with an advanced multi-directional obstacle avoidance system, which uses various sensors (such as ultrasonic sensors and visual sensors) to perceive surrounding environmental information in real time, promptly avoiding various obstacles during flight and ensuring flight safety and operational stability during UAV operations within the site.

[0116] Regarding the technical solution of this invention, the present invention aims to propose a novel inventive patent that organically integrates multiple technologies such as UAV technology, LiDAR technology, and data synthesis technology to form a highly efficient, intelligent, and accurate automatic laser coal inventory system. It aims to solve the high cost problem faced by conventional fixed coal inventory instruments when covering multiple locations. By adopting a flexible operation method of using UAVs equipped with LiDAR, it reduces reliance on a large number of fixed devices, lowering the costs of equipment purchase, installation, and maintenance. It also focuses on solving the problem of short battery life when UAVs are equipped with LiDAR, ensuring that UAVs still have sufficient battery life to complete coal inventory tasks over a large area of ​​coal yards, thereby improving operational efficiency and system practicality.

[0117] The functions of the UAV-based laser coal reconnaissance system are all performed by computer equipment, which includes one or more processors and one or more memories. The one or more memories store at least one piece of program code, which is loaded and executed by the one or more processors to realize the functions of the UAV-based laser coal reconnaissance system.

[0118] The processor fetches instructions from memory one by one, analyzes the instructions, and then performs the corresponding operations according to the instructions, generating a series of control commands to enable the various parts of the computer to act automatically, continuously, and in a coordinated manner, forming an organic whole. This enables the input of programs and data, as well as the calculation and output of results. The arithmetic or logical operations generated in this process are all performed by the arithmetic unit. The memory includes a read-only memory (ROM), which is used to store computer programs. The memory is protected by an external protection device.

[0119] For example, a computer program can be divided into one or more modules, one or more of which are stored in memory and executed by a processor to perform the present invention. The one or more modules can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a terminal device.

[0120] Those skilled in the art will understand that the above description of the service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0121] The processor can 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. A general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the terminal device, connecting various parts of the user terminal via various interfaces and lines.

[0122] The aforementioned memory can be used to store computer programs and / or modules. The aforementioned processor implements various functions of the aforementioned terminal device by running or executing the computer programs and / or modules stored in the memory, and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as information collection template display function, product information publishing function, etc.); the data storage area may store data created based on the use of the berth status display system (such as product information collection templates corresponding to different product types, product information that different product providers need to publish, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0123] If the modules / units integrated into the terminal device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the modules / units in the systems of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the functions of the various system embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0124] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0125] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A laser coal counting system based on unmanned aerial vehicles (UAVs), characterized in that, The system includes: The coal pile range determination module is used to acquire a blurred image of the coal pile containing image parameters based on a preset fixed camera, analyze the blurred image, and determine the range of the coal pile. The top-view image acquisition module is used to determine the detection path based on the range of the coal pile, and acquire a top-view image of the coal pile containing its location and time according to the detection path; The inspection path determination module is used to identify the top-view image, determine the coal pile distribution information, and determine the inspection path of the UAV based on the coal pile distribution information; wherein, the height of the inspection path is less than the height of the detection path. The 3D coal pile creation module is used to send the inspection path to the drone, receive the point cloud data fed back by the drone, and create a 3D coal pile based on the point cloud data. The display module is used to display the created 3D coal pile; The coal pile range determination module includes: The instruction sending unit is used to query the preset fixed camera and send a shooting instruction to the fixed camera; A blurred image receiving unit is used to receive images fed back from a fixed camera as blurred images. The parameter receiving unit is used to receive image parameters when the fixed camera acquires a blurred image, the image parameters including the image acquisition direction and acquisition wide angle; The image analysis unit is used to analyze blurry images and determine the extent of the coal pile. The analysis of the blurred image to determine the extent of the coal pile includes: Locating the boundary line of a coal pile in a blurred image based on the color value of the coal pile; The coal pile boundary line is mapped onto the horizontal plane based on the image parameters to obtain the horizontal mapping line; By statistically analyzing the horizontal mapping lines corresponding to the boundary lines of all coal piles, the planar profile can be obtained. The planar outline is expanded according to a preset ratio, and the expanded planar outline is used as the range of the coal pile.

2. The UAV-based laser coal inventory system according to claim 1, characterized in that, The top-view image acquisition module includes: The maximum altitude determination unit is used to query the image acquisition accuracy of the UAV and determine the maximum altitude based on the image acquisition accuracy and the detection range at different altitudes. The path creation unit is used to create a detection path based on the maximum altitude; the sum of the image acquisition range of the UAV on the detection path is greater than the range of the coal pile. The top-view image receiving unit is used to send the detection path to the UAV and receive the top-view image containing position and time from the UAV.

3. The UAV-based laser discing system of claim 1, wherein, The inspection path determination module includes: The stitching unit is used to acquire the most recent images at each location and stitch them together according to their positional relationships to obtain the overall image. The contour recognition unit is used to locate the boundary line of the coal pile in a blurred image based on the color value of the coal pile, and obtain the contour of the coal pile. The contour application unit is used to determine the inspection path of the UAV based on the obtained coal pile contour.

4. The UAV-based laser discing system of claim 3, wherein, The process of determining the UAV inspection path based on the obtained coal pile outline includes: To query the detection altitude range of the laser device built into the drone; Select the minimum height within the detection height range to obtain the single detection area of ​​the UAV at the minimum height; The coal pile outline is divided into several strip areas based on a single detection area in a preset direction; Select the center line of the strip area as the inspection path.

5. The UAV-based laser discing system of claim 1, wherein, The three-dimensional coal pile creation module includes: The point cloud data receiving unit is used to send the inspection path to the drone and receive the point cloud data fed back by the drone. A 3D coal pile creation unit is used to create a 3D coal pile based on the point cloud data and the identified coal pile outline. The point cloud data is obtained by a lidar mounted on the UAV.

6. The UAV-based laser discing system of claim 5, wherein, The three-dimensional coal pile creation module also includes: The point cloud data recording unit is used to record the point cloud data acquired by all drones at various locations when the number of drones is not unique. The difference calculation unit is used to compare the point cloud data acquired by all drones at the same location and calculate the difference. A probability determination unit is used to determine the sampling probability of each location based on the difference degree; the sampling probability is directly proportional to the difference degree. The decision unit is used to determine whether to acquire point cloud data for any UAV when it moves to a certain position, based on the acquisition probability.

7. The UAV-based laser disk mapping system of claim 1, wherein, The display module includes: The statistical unit is used to acquire and statistically analyze the three-dimensional coal pile at different times within a preset time period; The duration determination unit is used to receive the display period set by the administrator, calculate the ratio of the time period to the display period, and determine the display duration of the three-dimensional coal pile at each moment. The display execution unit is used to cyclically display the three-dimensional coal pile.

8. The UAV-based laser disk mapping system of claim 1, wherein, The UAV has a built-in obstacle avoidance module. When an obstacle avoidance action occurs, it records the obstacle avoidance location and generates an information acquisition interruption signal. After the obstacle avoidance is completed, it returns to the obstacle avoidance location and ends the information acquisition interruption signal.

Images