Method and device for processing point cloud data in roadway of underground mine

Abstract

The embodiments of the present application disclose a method and device for processing point cloud data in an underground mine roadway. A specific implementation manner of the method includes: obtaining the original point cloud data collected by a vehicle in an underground mine roadway; preprocessing the original point cloud data; for the preprocessed point cloud data, taking the vehicle body coordinate system as the center, setting the grid size, the number of horizontal grids, and the number of longitudinal index grids, and calculating the position of the grid where the point cloud is located according to the X value and Y value of the point cloud; according to the position of the grid where the point cloud is located, retaining the point cloud data within a preset region of interest to obtain the top grid and the ground grid of the underground mine roadway to be optimized; filtering the top grid and the ground grid to be optimized based on continuity. This implementation manner realizes the filtering of the top and the ground in the complex environment of the underground mine, and avoids the problem of misidentification of the ground and the top in autonomous driving.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a method and device for processing point cloud data in the roadway of an underground coal mine. Background Art

[0002] In the era of Industry 4.0, autonomous driving technology plays an increasingly important role in the intelligent development of underground coal mines. Accurate perception in complex underground coal mines is the most core link of autonomous driving, and the main difficulty is to accurately identify the top and ground of the roadway in the underground coal mine. Due to the complex environment in the underground coal mine, large fluctuations in the roadway, pipelines and signs on the roadway wall, sparse point clouds in the distance, etc., the existing ground filtering methods are difficult to ensure good results. For example, Random Sample Consensus (RANSAC) plane fitting fits the plane equation by random sampling and iteration, but the method is only applicable to flat ground, and the fitting effect is poor when the road is rough. In addition, there are emerging ground filtering methods such as patchwok++, which require ensuring that enough point clouds are recognized on the ground. However, the ground points recognized by lidar in the underground coal mine are scarce or even non-existent, so it is not applicable to the underground coal mine environment. Therefore, there is an urgent need for a roadway top and ground filtering algorithm suitable for the complex environment of underground coal mines. Summary of the Invention

[0003] The embodiments of the present application propose a method and device for processing point cloud data in the roadway of an underground coal mine.

[0004] In a first aspect, some embodiments of the present application provide a method for processing point cloud data in the roadway of an underground coal mine, the method including: obtaining the original point cloud data collected by a vehicle in the roadway of the underground coal mine; preprocessing the original point cloud data; for the preprocessed point cloud data, taking the vehicle body coordinate system as the center, setting the grid size, the number of horizontal grids, and the number of longitudinal index grids, and calculating the position of the grid where the point cloud is located according to the X value and Y value of the point cloud; according to the position of the grid where the point cloud is located, retaining the point cloud data within a preset region of interest to obtain the top grid and the ground grid of the roadway of the underground coal mine to be optimized; filtering the top grid and the ground grid to be optimized based on continuity.

[0005] In some embodiments, the filtering the top grid and the ground grid to be optimized based on continuity includes: for the top grid in the area above the vehicle body, counting the highest point of each horizontal row of grids; determining whether the Z value of the lowest point among the counted highest points is less than a preset top grid threshold; if so, determining the lowest point among the counted highest points as the optimized top grid in the area above the vehicle body; if not, determining the top grid threshold as the optimized top grid in the area above the vehicle body.

[0006] In some embodiments, the continuous filtering of the top grid and the ground grid to be optimized includes: for the top grid in the first preset extension area forward or backward above the vehicle body, starting from the horizontal row adjacent to the area above the vehicle body, the minimum value of each horizontal row of grids is statistically calculated. If there is no point cloud in a horizontal row, no statistics are made. If the difference between the minimum value of the horizontal row and the minimum value of the previous horizontal row is not greater than the first change threshold, the minimum value of the horizontal row is determined as the lowest point at the top of the horizontal row. If the difference between the minimum value of the horizontal row and the minimum value of the previous horizontal row is greater than the first change threshold, the lowest point at the top of the horizontal row is determined based on the minimum value of the previous horizontal row and the first change threshold, where the first change threshold is calculated based on a preset top slope; based on the obtained lowest points at the top, the points in the top grid of the first preset extension area with a Z value greater than the corresponding lowest point at the top are filtered out.

[0007] In some embodiments, the continuous filtering of the top grid and the ground grid to be optimized includes: for the ground grid in the area below the vehicle body, the average value of the lowest points in the grid is calculated and compared with a preset ground threshold. If the difference between the calculated average value of the lowest points and the ground threshold is within a preset range, the calculated average value of the lowest points is set as the lowest point on the ground of the grid. If the difference between the calculated average value of the lowest points and the ground threshold is not within the preset range, the ground threshold is set as the lowest point on the ground of the grid;

[0008] For the grids in the second preset extension area forward and backward of the vehicle body, the average value of the Z - axis of the points ranked after a preset value in terms of height in the grid is statistically calculated, and the average value of the Z - axis is compared with the ground threshold. If the average value of the Z - axis is greater than the ground threshold, the ground threshold is used as the lowest point on the ground of the grid; if the average value of the Z - axis is not greater than the ground threshold, the average value of the Z - axis is used as the lowest point on the ground of the grid; for the ground grids other than the area below the vehicle body and the second preset extension area, the minimum value in the grid is determined as the lowest point on the ground of the grid.

[0009] In some embodiments, the continuous filtering of the top grid and the ground grid to be optimized includes: for each horizontal row of the ground grid in a preset near - range, the highest value of the lowest points on the ground of the horizontal row is used as the lowest point on the ground of the horizontal row; for each horizontal row of the ground grid in a preset far - range, the lowest value of the lowest points on the ground of the horizontal row is used as the lowest point on the ground of the horizontal row.

[0010] In some embodiments, the continuous filtering of the top grid and the ground grid to be optimized includes: for the ground grid except the area under the vehicle body, starting from the horizontal row adjacent to the area under the vehicle body, determining whether the difference between the lowest ground point of this horizontal row and the lowest ground point of the previous horizontal row is greater than a second change threshold, where the second change threshold is calculated based on a preset ground slope; if so, modifying the lowest ground point of this horizontal row according to the lowest ground point of the previous horizontal row and the second change threshold; if not, retaining the lowest ground point of this horizontal row.

[0011] In some embodiments, the continuous filtering of the top grid and the ground grid to be optimized includes: filtering the ground grid based on the lowest ground point in the ground grid, the vehicle body height, and the filtered top grid.

[0012] In some embodiments, the method further includes: performing secondary filtering on the filtered ground grid based on intensity; for the ground grid after secondary filtering, sequentially updating the grids near the vehicle body and the grids far from the vehicle body based on continuity; performing secondary filtering on the filtered top grid based on the updated ground grid and the vehicle body height.

[0013] In a second aspect, some embodiments of the present application provide a processing device for point cloud data in an underground mine roadway. The device includes: an acquisition unit configured to acquire the original point cloud data collected by a vehicle in the underground mine roadway; a preprocessing unit configured to preprocess the original point cloud data; a rasterization unit configured to, for the preprocessed point cloud data, set a raster size, a number of horizontal rasters, and a number of longitudinal index rasters with the vehicle body coordinate system as the center, and calculate the position of the point cloud in the raster according to the X value and Y value of the point cloud; a screening unit configured to retain the point cloud data within a preset region of interest according to the position of the point cloud in the raster to obtain the top grid and the ground grid of the underground mine roadway to be optimized; a filtering unit configured to filter the top grid and the ground grid to be optimized based on continuity.

[0014] In some embodiments, the filtering unit is further configured to: for the top grid in the area above the vehicle body, count the highest point of each horizontal row of grids; determine whether the Z value of the lowest point among the counted highest points is less than a preset top grid threshold; if so, determining the lowest point among the counted highest points as the optimized top grid in the area above the vehicle body; if not, determining the top grid threshold as the optimized top grid in the area above the vehicle body.

[0015] In some embodiments, the filtering unit is further configured to: for the top grid of the first preset extension area in the forward or backward direction above the vehicle body, starting from the horizontal row adjacent to the area above the vehicle body, count the minimum value of each horizontal row of the grid. If there is no point cloud in a horizontal row, no statistics are made. If the difference between the minimum value of this horizontal row and the minimum value of the previous horizontal row is not greater than the first change threshold, then determine the minimum value of this horizontal row as the top lowest point of this horizontal row. If the difference between the minimum value of this horizontal row and the minimum value of the previous horizontal row is greater than the first change threshold, then determine the top lowest point of this horizontal row according to the minimum value of the previous horizontal row and the first change threshold, where the first change threshold is calculated based on a preset top slope; based on the obtained top lowest points, filter out the points in the top grid of the first preset extension area whose Z value is greater than the corresponding top lowest point.

[0016] In some embodiments, the filtering unit is further configured to: for the ground grid in the area below the vehicle body, calculate the average value of the lowest points in the grid, and compare the calculated average value of the lowest points with a preset ground threshold. If the difference between the calculated average value of the lowest points and the ground threshold is within a preset range, then set the calculated average value of the lowest points as the ground lowest point of this grid. If the difference between the calculated average value of the lowest points and the ground threshold is not within the preset range, then set the ground threshold as the ground lowest point of this grid;

[0017] For the grid in the second preset extension area in the forward and backward directions of the vehicle body, count the average value of the Z-axis of the points ranked after a preset value in the grid, and compare the average value of the Z-axis with the ground threshold. If the average value of the Z-axis is greater than the ground threshold, then use the ground threshold as the ground lowest point of this grid; if the average value of the Z-axis is not greater than the ground threshold, then use the average value of the Z-axis as the ground lowest point of this grid; for the ground grid except the area below the vehicle body and the second preset extension area, determine the minimum value in the grid as the ground lowest point of this grid.

[0018] In some embodiments, the filtering unit is further configured to: for each horizontal row of the ground grid in a preset near range, use the highest value of the ground lowest points of this horizontal row as the ground lowest point of this horizontal row; for each horizontal row of the ground grid in a preset far range, use the lowest value of the ground lowest points of this horizontal row as the ground lowest point of this horizontal row.

[0019] In some embodiments, the filtering unit is further configured to: for the ground grid except the area under the vehicle body, starting from the horizontal row adjacent to the area under the vehicle body, determine whether the difference between the lowest ground point of this horizontal row and the lowest ground point of the previous horizontal row is greater than a second change threshold, where the second change threshold is calculated based on a preset ground slope; if so, modify the lowest ground point of this horizontal row according to the lowest ground point of the previous horizontal row and the second change threshold; if not, retain the lowest ground point of this horizontal row.

[0020] In some embodiments, the filtering unit is further configured to: filter the ground grid based on the lowest ground point in the ground grid, the vehicle body height, and the filtered top grid.

[0021] In some embodiments, the device further includes a secondary filtering unit, which is configured to: perform secondary filtering on the filtered ground grid based on intensity; for the ground grid after secondary filtering, sequentially perform vehicle body adjacent grid update and ground far grid update based on continuity; perform secondary filtering on the filtered top grid based on the updated ground grid and the vehicle body height.

[0022] In a third aspect, some embodiments of the present application provide a device, including: one or more processors; a storage device on which one or more programs are stored, and when the above one or more programs are executed by the above one or more processors, the above one or more processors implement the method as described in the first aspect above.

[0023] In a fourth aspect, some embodiments of the present application provide a computer-readable medium, on which a computer program is stored, and when the program is executed by a processor, it implements the method as described in the first aspect above.

[0024] The method and device for processing point cloud data in an underground mine roadway provided by the embodiments of the present application obtain the original point cloud data collected by a vehicle in an underground mine roadway; preprocess the original point cloud data; for the preprocessed point cloud data, with the vehicle body coordinate system as the center, set the grid size, the number of horizontal grids, and the number of longitudinal index grids, and calculate the position of the grid where the point cloud is located according to the X value and Y value of the point cloud; according to the position of the grid where the point cloud is located, retain the point cloud data within a preset region of interest to obtain the top grid and ground grid of the underground mine roadway to be optimized; filter the top grid and ground grid to be optimized based on continuity, realizing the filtering of the top and ground in the complex environment of the underground mine, and avoiding the problem of misidentification of the ground and top in autonomous driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, objects, and advantages of the present application will become more apparent:

[0026] Figure 1 are some exemplary system architecture diagrams to which the present application can be applied;

[0027] Figure 2 is a flowchart of an embodiment of a method for processing point cloud data in an underground mine roadway according to the present application;

[0028] Figure 3 is a schematic structural diagram of an embodiment of a device for processing point cloud data in an underground mine roadway according to the present application;

[0029] Figure 4 is a schematic structural diagram of a computer system of a device suitable for implementing some embodiments of the present application. Detailed implementation manners

[0030] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related invention, rather than limiting the invention. Additionally, it should be noted that for the sake of description, only parts related to the relevant invention are shown in the drawings.

[0031] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the drawings and embodiments.

[0032] Figure 1 An exemplary system architecture 100 is shown for embodiments of a method for processing point cloud data in an underground mine roadway or a device for processing point cloud data in an underground mine roadway to which the present application can be applied.

[0033] As Figure 1 shown, the system architecture 100 may include a vehicle 101, a network 102, and a server 103 that provides support for the vehicle 101. The vehicle 101 may be an underground transport vehicle. A lidar device 104 and various vehicle-mounted sensors may be provided in the vehicle 101. The network 102 is used as a medium to provide a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types. The lidar device 104 may collect point cloud data in the roadway.

[0034] Server 103 can be a server that provides various services, such as a server for processing the point cloud data collected by lidar device 104. It should be noted that the server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers or as a single server. When the server is software, it can be implemented as multiple software or software modules (such as those used to provide distributed services) or as a single software or software module. Specific limitations are not made here. It should be pointed out that the point cloud data collected by the lidar device 104 can also be processed by an in-vehicle intelligent device. In this case, the above system architecture 100 may not have the network 102 and the server 103.

[0035] It should be understood that Figure 1 the numbers of vehicles, lidar devices, networks, and servers in

[0036] Continuing to refer to Figure 2 , a flowchart 200 of an embodiment of the method for processing point cloud data in an underground mine roadway according to the present application is shown. The method for processing point cloud data in an underground mine roadway includes the following steps:

[0037] Step 201, obtain the original point cloud data collected by a vehicle in an underground mine roadway.

[0038] In this embodiment, a vehicle traveling in an underground mine roadway can collect original point cloud data through devices such as lidar.

[0039] Step 202, preprocess the original point cloud data.

[0040] In this embodiment, the preprocessing can include operations such as noise removal, downsampling, filtering, and point cloud completion, and different preprocessing operations can be selected according to the characteristics of the original point cloud. As an example, if the original point cloud has a large quantity and many abnormal noise points, different intensity values can be used for filtering according to the intensity characteristics of the radar at different distances to reduce the number of abnormal points, and then uniform downsampling can be used to reduce the point cloud quantity, and abnormal points can be filtered out through radius filtering.

[0041] Step 203, for the preprocessed point cloud data, with the vehicle body coordinate system as the center, set the grid size, the number of horizontal grids, and the number of longitudinal index grids, and calculate the position of the grid where the point cloud is located according to the X value and Y value of the point cloud.

[0042] In this embodiment, for the preprocessed point cloud data, with the vehicle body coordinate system as the center, set the grid size, the number of horizontal grids, and the number of longitudinal index grids, and calculate the position of the grid where the point cloud is located according to the X value and Y value of the point cloud.

[0043] Step 204: According to the positions of the grids where the point clouds are located, retain the point cloud data within a preset region of interest to obtain the top grids and ground grids of the underground mine roadway to be optimized.

[0044] In this embodiment, according to the positions of the grids where the point clouds are located, retain the point cloud data within a preset region of interest to obtain the top grids and ground grids of the underground mine roadway to be optimized, so as to project the preprocessed point cloud data into the top grids and ground grids. As an example, according to the design of the roadway and actual application requirements, an area of interest of the top grids and ground grids to be retained can be defined by setting a bounding box or using a specific geometric shape.

[0045] Step 205: Filter the top grids and ground grids to be optimized based on continuity.

[0046] In this embodiment, filtering the top grids and ground grids to be optimized based on continuity can remove untrue or abnormal elevation values generated due to noise or irregularities in the data acquisition process. The top grids and ground grids to be optimized can be filtered as a whole based on continuity, or the top grids and ground grids can be optimized and filtered by region according to the characteristics of the point cloud data in different regions. As an example, the regions can be based on distance or whether there are blind spots of the lidar. For example, there are blind spots of the lidar in the space above or below the vehicle body.

[0047] In some optional implementation manners of this embodiment, filtering the top grids and ground grids to be optimized based on continuity includes: for the top grids in the area above the vehicle body, count the highest points of the grids in each horizontal row; determine whether the Z value of the lowest point among the counted highest points is less than a preset top grid threshold; if so, determine the lowest point among the counted highest points as the optimized top grid in the area above the vehicle body; if not, determine the top grid threshold as the optimized top grid in the area above the vehicle body. The area above the vehicle body can be obtained by projecting the vehicle body corner points. There are blind spots of the lidar in the space above the vehicle body, and this area does not affect the vehicle operation. The top grid threshold can be set according to the experience of the staff or by referring to data such as the vehicle body height and roadway height.

[0048] In some alternative implementation manners of this embodiment, filtering the top grid and the ground grid to be optimized based on continuity includes: for the top grid in the first preset extension area forward or backward above the vehicle body, starting from the horizontal row adjacent to the area above the vehicle body, counting the minimum value of each horizontal row of grids. If there is no point cloud in a horizontal row, no statistics are made. If the difference between the minimum value of this horizontal row and the minimum value of the previous horizontal row is not greater than the first change threshold, the minimum value of this horizontal row is determined as the top lowest point of this horizontal row. If the difference between the minimum value of this horizontal row and the minimum value of the previous horizontal row is greater than the first change threshold, the top lowest point of this horizontal row is determined according to the minimum value of the previous horizontal row and the first change threshold, where the first change threshold is calculated based on the preset top slope; based on the obtained top lowest points, filter out the points in the top grid of the first preset extension area whose Z value is greater than the corresponding top lowest point. The first preset extension area can be an area relatively close to the vehicle body, which can be set according to the experience of the staff or with reference to information such as point cloud quality. The top slope can be set with reference to the actual situation of the roadway. Filtering based on continuity can ensure the coherence of passing through the top of the roadway and solve the misidentification due to the uphill and downhill of the top of the roadway.

[0049] In some alternative implementation manners of this embodiment, filtering the top grid and the ground grid to be optimized based on continuity includes: for the ground grid in the area below the vehicle body, calculating the average value of the lowest points in the grid and comparing the calculated average value of the lowest points with the preset ground threshold. If the difference between the calculated average value of the lowest points and the ground threshold is within the preset range, the calculated average value of the lowest points is set as the ground lowest point of this grid. If the difference between the calculated average value of the lowest points and the ground threshold is not within the preset range, the ground threshold is set as the ground lowest point of this grid; the area below the vehicle body can be obtained by projecting the vehicle body corner points. Considering that the vehicle body may be in a puddle or a water channel, but the vehicle itself is driving on a normal road, so the lowest points of the grids within a certain range below the vehicle body can be averaged and compared with the ground threshold.

[0050] For the grids in the second preset extension area in the forward and backward directions of the vehicle body, calculate the average value of the Z-axis of the points whose height ranks after the preset value in the grid, compare the average value of the Z-axis with one-third. If the average value of the Z-axis is greater than the ground threshold, use the ground threshold as the lowest ground point of the grid; if the average value of the Z-axis is not greater than the ground threshold, use the average value of the Z-axis as the lowest ground point of the grid. For the ground grids except the area under the vehicle body and the second preset extension area, determine the minimum value in the grid as the lowest ground point of the grid. The first preset extension area can be an area relatively close to the vehicle body, which can be set according to the experience of the staff or with reference to information such as point cloud quality. The preset value can be set according to the experience of the staff or the characteristics of the roadway. As an example, it can be one-third, that is, the points whose height ranks in the last one-third can be counted. The ground threshold can be 0 or a value close to the ground zero point.

[0051] In some alternative implementation manners of this embodiment, filtering the top grids and ground grids to be optimized based on continuity includes: for each horizontal row of the ground grids within a preset near range, use the maximum value of the lowest ground points in this horizontal row as the lowest ground point of this horizontal row; for each horizontal row of the ground grids within a preset far range, use the minimum value of the lowest ground points in this horizontal row as the lowest ground point of this horizontal row. In the grids in the distance, it may be impossible to identify the ground, and the point cloud obtained at this time may actually be points on the wall. Therefore, use the minimum value of the lowest ground points in this horizontal row as the lowest ground point of this horizontal row.

[0052] In some alternative implementation manners of this embodiment, filtering the top grids and ground grids to be optimized based on continuity includes: for the ground grids except the area under the vehicle body, starting from the horizontal row adjacent to the area under the vehicle body, determine whether the difference between the lowest ground point in this horizontal row and the lowest ground point in the previous horizontal row is greater than the second change threshold, where the second change threshold is calculated based on the preset ground slope; if so, modify the lowest ground point in this horizontal row according to the lowest ground point in the previous horizontal row and the second change threshold; if not, retain the lowest ground point in this horizontal row.

[0053] In some alternative implementation manners of this embodiment, filtering the top grids and ground grids to be optimized based on continuity includes: filtering the ground grids based on the lowest ground points in the ground grids, the vehicle body height, and the filtered top grids. Considering that a vehicle needs to be able to pass between the ground and the top, the filtered top grids can be used to constrain the ground grids to ensure that the distance between the two is greater than the vehicle body height. For the points within a certain distance below the ground grids, filter the ground point cloud. Filtering the ground grids can solve problems such as the existence of drainage channels on the ground in underground coal mine roadways, the absence of lidar points on the distant ground, and uneven road surfaces.

[0054] In some alternative implementation manners of this embodiment, the method further includes: performing secondary filtering on the filtered ground grid based on intensity; for the ground grid after secondary filtering, sequentially performing grid update near the vehicle body and grid update far from the ground based on continuity; performing secondary filtering on the filtered top grid based on the updated ground grid and the vehicle body height. In the case where there are reflections on the ground of the far roadway, complex pipelines and road signs on the top of the roadway, which may lead to problems of misidentifying the ground, the top and the ground of the roadway can be corrected twice to achieve precise filtering. For the point cloud in the distance, due to the limitations of the sensor itself, there will be obvious reflections of walls or other obstacles. Some of these reflections are much lower than the ground, which affects the identification of the ground. Therefore, for the ground grid in the rough filtering algorithm, the point cloud below the grid is filtered twice based on intensity to obtain the updated points in each ground grid. For the updated points, the grid near the vehicle body is updated sequentially, and the grid far from the ground is updated. When updating the ground in the distance, the lowest point in each row can be used as the minimum value of that row, and when calculating the continuity between different rows, it can be considered that the change between different rows should be less than a certain threshold; for the top of the roadway, a certain height value can be added on the basis of the ground grid, so that the complex pipelines and suspended road signs on the top of the roadway can be filtered out.

[0055] The method provided in the above embodiment of this application obtains the original point cloud data collected by a vehicle in an underground mine roadway; preprocesses the original point cloud data; for the preprocessed point cloud data, with the vehicle body coordinate system as the center, sets the grid size, the number of horizontal grids, and the number of longitudinal index grids, and calculates the position of the grid where the point cloud is located according to the X value and Y value of the point cloud; according to the position of the grid where the point cloud is located, retains the point cloud data within a preset region of interest to obtain the top grid and the ground grid of the underground mine roadway to be optimized; filters the top grid and the ground grid to be optimized based on continuity, realizes the filtering of the top and the ground in the complex environment of the underground mine, and avoids the problem of misidentifying the ground and the top in autonomous driving.

[0056] Further referring to Figure 3 , as an implementation of the methods shown in the above figures, this application provides an embodiment of a device for processing point cloud data in an underground mine roadway. This device embodiment corresponds to Figure 2 the method embodiment shown, and this device can be specifically applied to various electronic devices.

[0057] As shown in Figure 3As shown in the figure, the processing device 300 for point cloud data in the roadway of an underground coal mine in this embodiment includes: an acquisition unit 301, a preprocessing unit 302, a rasterization unit 303, a screening unit 304, and a filtering unit 305. Among them, the acquisition unit is configured to acquire the original point cloud data collected by a vehicle in the roadway of an underground coal mine; the preprocessing unit is configured to preprocess the original point cloud data; the rasterization unit is configured to, for the preprocessed point cloud data, with the vehicle body coordinate system as the center, set the raster size, the number of horizontal rasters, and the number of longitudinal index rasters, and calculate the position of the raster where the point cloud is located according to the X value and Y value of the point cloud; the screening unit is configured to, according to the position of the raster where the point cloud is located, retain the point cloud data within a preset region of interest to obtain the top raster and the ground raster of the roadway of the underground coal mine to be optimized; the filtering unit is configured to filter the top raster and the ground raster to be optimized based on continuity.

[0058] In this embodiment, for the specific processing of the acquisition unit 301, the preprocessing unit 302, the rasterization unit 303, the screening unit 304, and the filtering unit 305 of the processing device 300 for point cloud data in the roadway of an underground coal mine, reference can be made to Figure 2 Steps 201, 202, 203, 204, and 205 in the corresponding embodiment.

[0059] In some alternative implementation manners of this embodiment, the filtering unit is further configured to: for the top raster in the area above the vehicle body, count the highest point of each raster in each horizontal row; determine whether the Z value of the lowest point among the counted highest points is less than a preset top raster threshold; if so, determine the lowest point among the counted highest points as the optimized top raster in the area above the vehicle body; if not, determine the top raster threshold as the optimized top raster in the area above the vehicle body.

[0060] In some alternative implementation manners of this embodiment, the filtering unit is further configured to: for the top raster in the first preset extension area in front of or behind the vehicle body, starting from the horizontal row adjacent to the area above the vehicle body, count the lowest value of each raster in each horizontal row. If there is no point cloud in this horizontal row, no statistics are made. If the difference between the lowest value of this horizontal row and the lowest value of the previous horizontal row is not greater than the first change threshold, determine the lowest value of this horizontal row as the lowest point at the top of this horizontal row. If the difference between the lowest value of this horizontal row and the lowest value of the previous horizontal row is greater than the first change threshold, determine the lowest point at the top of this horizontal row according to the lowest value of the previous horizontal row and the first change threshold, where the first change threshold is calculated based on a preset top slope; based on the obtained lowest point at the top, filter out the points in the top raster of the first preset extension area whose Z value is greater than the corresponding lowest point at the top.

[0061] In some alternative implementation manners of this embodiment, the filtering unit is further configured to: for the ground grids in the area below the vehicle body, calculate the average value of the lowest points in the grid, and compare the calculated average value of the lowest points with a preset ground threshold. If the difference between the calculated average value of the lowest points and the ground threshold is within a preset range, set the calculated average value of the lowest points as the ground lowest point of the grid; if the difference between the calculated average value of the lowest points and the ground threshold is not within the preset range, set the ground threshold as the ground lowest point of the grid;

[0062] For the grids in the second preset extension areas in the forward and backward directions of the vehicle body, statistically calculate the average value of the Z - axis of the points ranked after a preset value in the grid, and compare the average value of the Z - axis with the ground threshold. If the average value of the Z - axis is greater than the ground threshold, use the ground threshold as the ground lowest point of the grid; if the average value of the Z - axis is not greater than the ground threshold, use the average value of the Z - axis as the ground lowest point of the grid; for the ground grids except the area below the vehicle body and the second preset extension areas, determine the minimum value in the grid as the ground lowest point of the grid.

[0063] In some alternative implementation manners of this embodiment, the filtering unit is further configured to: for each horizontal row of the ground grids in a preset near - range, use the highest value of the ground lowest points of the row as the ground lowest point of the row; for each horizontal row of the ground grids in a preset far - range, use the lowest value of the ground lowest points of the row as the ground lowest point of the row.

[0064] In some alternative implementation manners of this embodiment, the filtering unit is further configured to: for the ground grids except the area below the vehicle body, starting from the horizontal row adjacent to the area below the vehicle body, determine whether the difference between the ground lowest point of this row and the ground lowest point of the previous row is greater than a second change threshold, where the second change threshold is calculated based on a preset ground slope; if so, modify the ground lowest point of this row according to the ground lowest point of the previous row and the second change threshold; if not, retain the ground lowest point of this row.

[0065] In some alternative implementation manners of this embodiment, the filtering unit is further configured to: filter the ground grids based on the ground lowest points in the ground grids, the vehicle body height, and the filtered top grids.

[0066] In some alternative implementation manners of this embodiment, the device further includes a secondary filtering unit, which is configured to: perform secondary filtering on the filtered ground grid based on intensity; for the ground grid after secondary filtering, update the grid near the vehicle body and the grid far from the ground in sequence based on continuity; and perform secondary filtering on the filtered top grid based on the updated ground grid and the vehicle body height. The device provided in the above embodiment of the present application obtains the original point cloud data collected by a vehicle in an underground mine roadway; preprocesses the original point cloud data; for the preprocessed point cloud data, sets the grid size, the number of horizontal grids, and the number of longitudinal index grids with the vehicle body coordinate system as the center, and calculates the position of the grid where the point cloud is located according to the X value and Y value of the point cloud; according to the position of the grid where the point cloud is located, retains the point cloud data within a preset region of interest to obtain the top grid and the ground grid of the underground mine roadway to be optimized; and filters the top grid and the ground grid to be optimized based on continuity, realizing the filtering of the top and the ground in the complex environment of the underground mine and avoiding the problem of misidentification of the ground and the top in autonomous driving.

[0067] Reference is made below to Figure 4 , which shows a schematic structural diagram of a computer system 400 suitable for use in implementing the embodiments of the present application. Figure 4 The device shown is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present application.

[0068] As Figure 4 shown, the computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage section 408 into the random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the system 400 are also stored. The CPU 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. The input / output (I / O) interface 405 is also connected to the bus 404.

[0069] The following components can be connected to the I / O interface 405: an input section 406 including, such as, a keyboard, a mouse, etc.; an output section 407 including, such as, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as required. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as required so that the computer program read from it can be installed into the storage section 408 as required.

[0070] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, the above-mentioned functions defined in the method of the present application are performed. It should be noted that the computer-readable medium described in the present application can be a computer-readable signal medium or a computer-readable medium or any combination of the two. The computer-readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable medium can include, but are not limited to: 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 of the above. In the present application, the computer-readable medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. And in the present application, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination of the above.

[0071] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the C language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone 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 can 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 it can be connected to an external computer (for example, by connecting through the Internet using an Internet service provider).

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks can occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0073] The units involved in the embodiments described in this application can be implemented in software or in hardware. The described units can also be provided in a processor. For example, it can be described as: a processor includes an acquisition unit, a first determination unit, a query unit, a second determination unit, and a control unit. Among them, the names of these units do not constitute a limitation on the unit itself in some cases. For example, the acquisition unit can also be described as "the unit for acquiring the original point cloud data collected by vehicles in an underground coal mine roadway".

[0074] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiments; or may exist separately without being assembled into the device. The above computer-readable medium carries one or more programs, and when the one or more programs are executed by the device, the device is caused to: acquire the original point cloud data collected by vehicles in the underground mine roadway; preprocess the original point cloud data; for the preprocessed point cloud data, with the vehicle body coordinate system as the center, set the grid size, the number of horizontal grids, and the number of longitudinal index grids, and calculate the position of the grid where the point cloud is located according to the X value and Y value of the point cloud; according to the position of the grid where the point cloud is located, retain the point cloud data within a preset region of interest to obtain the top grid and the ground grid of the underground mine roadway to be optimized; filter the top grid and the ground grid to be optimized based on continuity.

[0075] The above description is only the preferred embodiments of the present application and the description of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present application.

Claims

1. A method for processing point cloud data in an underground mine tunnel, characterized in that: include: Obtain the original point cloud data collected by vehicles in underground mine tunnels; Preprocessing the original point cloud data; For the preprocessed point cloud data, with the vehicle body coordinate system as the center, set the grid size, the number of horizontal grids, and the number of vertical index grids, and calculate the grid position of the point cloud according to the X and Y values ​​of the point cloud; According to the position of the grid where the point cloud is located, the point cloud data in the preset area of ​​interest is retained to obtain the top grid and the ground grid of the underground mine tunnel to be optimized; filtering the top grid and the ground grid to be optimized based on continuity; The filtering of the top grid and the ground grid to be optimized based on continuity includes: For the top grid of the area above the vehicle body, count the highest point of the grid in each horizontal row; Determine whether the Z value of the lowest point among the highest points obtained by statistics is less than the preset top grid threshold; If yes, the lowest point among the highest points obtained by statistics is determined as the top grid of the optimized area above the vehicle body; If not, the top grid threshold is determined as the top grid of the area above the optimized vehicle body; The filtering of the top grid and the ground grid to be optimized based on continuity includes: For the top grid of the first preset extension area in the forward or rearward direction above the vehicle body, starting from the horizontal row adjacent to the area above the vehicle body, the lowest value of the horizontal row is counted for the grids in each horizontal row. If there is no point cloud in the horizontal row, no statistics are performed. If the difference between the lowest value of the horizontal row and the lowest value of the previous horizontal row is not greater than a first change threshold, the lowest value of the horizontal row is determined as the lowest point of the top of the horizontal row. If the difference between the lowest value of the horizontal row and the lowest value of the previous horizontal row is greater than the first change threshold, the lowest point of the top of the horizontal row is determined according to the lowest value of the previous horizontal row and the first change threshold, wherein the first change threshold is calculated based on a preset top slope. Based on the obtained top lowest point, filtering out points in the top grid of the first preset extension area whose Z values ​​are greater than the corresponding top lowest point; The filtering of the top grid and the ground grid to be optimized based on continuity includes: For the ground grid in the area below the vehicle body, the average value of the lowest point in the grid is calculated, and the calculated average value of the lowest point is compared with a preset ground threshold value. If the difference between the calculated average value of the lowest point and the ground threshold value is within a preset range, the calculated average value of the lowest point is set as the ground lowest point of the grid. If the difference between the calculated average value of the lowest point and the ground threshold value is not within the preset range, the ground threshold value is set as the ground lowest point of the grid. For the grids of the second preset extension area forward and rearward of the vehicle body, the Z-axis average value of the points in the grid whose height ranks behind the preset value is counted, and the Z-axis average value is compared with the ground threshold value. If the Z-axis average value is greater than the ground threshold value, the ground threshold value is used as the lowest point of the grid; if the Z-axis average value is not greater than the ground threshold value, the Z-axis average value is used as the lowest point of the grid; For the ground grid except the area below the vehicle body and the second preset extension area, the minimum value in the grid is determined as the lowest point of the ground in the grid; The filtering of the top grid and the ground grid to be optimized based on continuity includes: For each horizontal row of the ground grid of the preset near range, the highest value of the lowest ground point of the horizontal row is used as the lowest ground point of the horizontal row; For each horizontal row of the ground grid of the preset distant range, the minimum value of the lowest ground point of the horizontal row is used as the lowest ground point of the horizontal row; The filtering of the top grid and the ground grid to be optimized based on continuity includes: For the ground grids other than the area under the vehicle body, starting from a horizontal row adjacent to the area under the vehicle body, determining whether a difference between the lowest point of the ground in the horizontal row and the lowest point of the ground in the previous horizontal row is greater than a second change threshold, wherein the second change threshold is calculated based on a preset ground slope; If yes, modify the lowest ground point of the row according to the lowest ground point of the previous row and the second change threshold; If not, the lowest ground point of the row is retained; The filtering of the top grid and the ground grid to be optimized based on continuity includes: The ground grid is filtered based on the lowest point of the ground in the ground grid, the height of the vehicle body, and the filtered top grid.

2. The method according to claim 1, characterized in that The method further comprises: The filtered ground grid is filtered again based on intensity; For the ground grid after secondary filtering, the grid near the vehicle body and the grid far from the ground are updated in sequence based on continuity; Based on the updated ground grid and the vehicle height, a secondary filtering of the filtered top grid is performed.

3. A device for processing point cloud data in a mine tunnel, characterized in that: include: An acquisition unit is configured to acquire original point cloud data collected by a vehicle in an underground mine tunnel; A preprocessing unit, configured to preprocess the original point cloud data; The rasterization unit is configured to set the grid size, the number of horizontal grids, and the number of vertical index grids for the preprocessed point cloud data with the vehicle body coordinate system as the center, and calculate the position of the grid where the point cloud is located according to the X value and Y value of the point cloud; A screening unit is configured to retain the point cloud data in a preset area of ​​interest according to the position of the grid where the point cloud is located to obtain the top grid and the ground grid of the underground mine tunnel to be optimized; A filtering unit configured to filter the top grid and the ground grid to be optimized based on continuity; Wherein, the filtering unit is further configured as follows: For the top grid of the area above the vehicle body, count the highest point of the grid in each horizontal row; Determine whether the Z value of the lowest point among the highest points obtained by statistics is less than the preset top grid threshold; If yes, the lowest point among the highest points obtained by statistics is determined as the top grid of the optimized area above the vehicle body; If not, the top grid threshold is determined as the top grid of the area above the optimized vehicle body; The filtering of the top grid and the ground grid to be optimized based on continuity includes: For the top grid of the first preset extension area in the forward or rearward direction above the vehicle body, starting from the horizontal row adjacent to the area above the vehicle body, the lowest value of the horizontal row is counted for the grids in each horizontal row. If there is no point cloud in the horizontal row, no statistics are performed. If the difference between the lowest value of the horizontal row and the lowest value of the previous horizontal row is not greater than a first change threshold, the lowest value of the horizontal row is determined as the lowest point of the top of the horizontal row. If the difference between the lowest value of the horizontal row and the lowest value of the previous horizontal row is greater than the first change threshold, the lowest point of the top of the horizontal row is determined according to the lowest value of the previous horizontal row and the first change threshold, wherein the first change threshold is calculated based on a preset top slope. Based on the obtained top lowest point, filtering out points in the top grid of the first preset extension area whose Z values ​​are greater than the corresponding top lowest point; The filtering of the top grid and the ground grid to be optimized based on continuity includes: For the ground grid in the area below the vehicle body, the average value of the lowest point in the grid is calculated, and the calculated average value of the lowest point is compared with a preset ground threshold value. If the difference between the calculated average value of the lowest point and the ground threshold value is within a preset range, the calculated average value of the lowest point is set as the ground lowest point of the grid. If the difference between the calculated average value of the lowest point and the ground threshold value is not within the preset range, the ground threshold value is set as the ground lowest point of the grid. For the grids of the second preset extension area forward and rearward of the vehicle body, the Z-axis average value of the points in the grid whose height ranks behind the preset value is counted, and the Z-axis average value is compared with the ground threshold value. If the Z-axis average value is greater than the ground threshold value, the ground threshold value is used as the lowest point of the grid; if the Z-axis average value is not greater than the ground threshold value, the Z-axis average value is used as the lowest point of the grid; For the ground grid except the area below the vehicle body and the second preset extension area, the minimum value in the grid is determined as the lowest point of the ground in the grid; The filtering of the top grid and the ground grid to be optimized based on continuity includes: For each horizontal row of the ground grid of the preset near range, the highest value of the lowest ground point of the horizontal row is used as the lowest ground point of the horizontal row; For each horizontal row of the ground grid of the preset distant range, the minimum value of the lowest ground point of the horizontal row is used as the lowest ground point of the horizontal row; The filtering of the top grid and the ground grid to be optimized based on continuity includes: For the ground grids other than the area under the vehicle body, starting from a horizontal row adjacent to the area under the vehicle body, determining whether a difference between the lowest point of the ground in the horizontal row and the lowest point of the ground in the previous horizontal row is greater than a second change threshold, wherein the second change threshold is calculated based on a preset ground slope; If yes, modify the lowest ground point of the row according to the lowest ground point of the previous row and the second change threshold; If not, the lowest ground point of the row is retained; The filtering of the top grid and the ground grid to be optimized based on continuity includes: The ground grid is filtered based on the lowest point of the ground in the ground grid, the height of the vehicle body, and the filtered top grid.

Images