Tunnel point cloud data processing method and system

Abstract

The tunnel point cloud data processing method and system provided in the present application realize point cloud data collection for the tunnel through the cooperation of a first movable device for executing point cloud data collection and a second movable device equipped with a preset stereo reference object, and then splicing the point cloud data according to the point cloud position information related to the stereo reference object in the collected point cloud data. The point cloud data can be spliced ​​more accurately and the spatial position relationship of the point cloud data segments with complete time can be retained.

Description

Technical Field

[0001] The present application relates to the field of machine vision technology, and more specifically, to a method and system for processing tunnel point cloud data. Background Art

[0002] Tunnel lining inspection is very important for timely discovering tunnel hidden dangers and maintaining tunnel safety. In order to quickly and effectively inspect the tunnel lining, some existing technologies use laser scanning to obtain point cloud data inside the tunnel, and the status of the tunnel lining can be analyzed and determined based on the point cloud data. Among them, the scanning range of the laser scanning equipment is limited, and the extension length of the tunnel is generally large. Therefore, it is necessary to perform multiple laser scanning operations at different positions in the tunnel, and then splice the obtained point cloud data. However, the existing tunnel point cloud data splicing methods have the problem of low splicing accuracy or the partial spatial relationship of the point cloud data after splicing, which affects the subsequent analysis of the tunnel based on the point cloud data. Summary of the invention

[0003] In order to overcome the above-mentioned deficiencies in the prior art, the purpose of the present application is to provide a tunnel point cloud data processing method, the method comprising:

[0004] Controlling a first movable device to move to a first position in a target tunnel, and collecting point cloud data of a first target area to obtain first point cloud data; the first target area includes a first area to be spliced;

[0005] Controlling a second movable device carrying a preset three-dimensional reference object to move to the first area to be spliced ​​and then remain stationary;

[0006] Controlling the first movable device to collect point cloud data of the first target area again to obtain second point cloud data;

[0007] Controlling the first movable device to move to a second position in the target tunnel, and collecting point cloud data of a second target area in the target tunnel to obtain third point cloud data; the second target area includes the first area to be spliced;

[0008] Controlling the second movable device to move out of the first area to be spliced;

[0009] Controlling the first movable device to collect point cloud data of the second target area again to obtain fourth point cloud data;

[0010] Determine a collection coordinate mapping relationship between the first position and the second position according to the second point cloud data, the third point cloud data and the pre-configured shape parameters of the three-dimensional reference object;

[0011] The first point cloud data and the fourth point cloud data are spliced ​​according to the acquisition coordinate mapping relationship.

[0012] In some possible implementations, the step of determining the acquisition coordinate mapping relationship between the first position and the second position according to the second point cloud data, the third point cloud data, and the pre-configured shape parameters of the three-dimensional reference object includes:

[0013] Determining point information corresponding to the three-dimensional reference object from the second point cloud data and the third point cloud data respectively according to the shape parameters of the three-dimensional reference object;

[0014] Based on the point information of the three-dimensional reference object in the second point cloud data and the third point cloud data, point alignment processing is performed on the second point cloud data and the third point cloud data to obtain a collection coordinate mapping relationship between the first position and the second position.

[0015] In some possible implementations, after the step of determining point information corresponding to the stereoscopic reference object from the second point cloud data and the third point cloud data respectively according to the shape parameters of the stereoscopic reference object, the method further includes:

[0016] According to the point information corresponding to the stereoscopic reference object in the second point cloud data and the third point cloud data and the shape parameters of the stereoscopic reference object, point reconstruction and completion are performed on the positions of the stereoscopic reference object in the second point cloud data and the third point cloud data that have not been collected to obtain the point information of the stereoscopic reference object after point reconstruction and completion.

[0017] In some possible implementations, the first movable device includes a laser point cloud acquisition device that can move on the ground or on a ground track; the three-dimensional reference object includes a regular tetrahedron, and when the three-dimensional reference object is mounted on the second movable device, one cone angle faces downward.

[0018] In some possible implementations, the second movable device includes a horizontal tilt angle adjustment device, and the horizontal tilt angle adjustment device is used to keep the horizontal tilt angles of the three-dimensional reference object at different positions consistent.

[0019] In some possible implementations, the second movable device includes a drone; and the step of controlling the second movable device carrying the preset three-dimensional reference object to move to the first area to be spliced ​​includes:

[0020] A drone with a preset three-dimensional reference object fixedly mounted thereon is controlled to move to the first area to be spliced ​​and to hover at a fixed position.

[0021] In some possible implementation manners, the point density of the first point cloud data and the fourth point cloud data is greater than that of the second point cloud data and the third point cloud data.

[0022] In some possible implementation manners, the second target area further includes a second area to be spliced, and the second area to be spliced does not overlap with the first area to be spliced; the step of controlling the second movable device to move out of the first area to be spliced includes:

[0023] Controlling the second movable device to move from the first area to be spliced to the second area to be spliced;

[0024] After the step of controlling the first movable device to collect point cloud data for the second target area again to obtain fourth point cloud data, the method further includes:

[0025] Controlling the first movable device to move to a third position in the target tunnel and collecting point cloud data for a third target area in the target tunnel to obtain fifth point cloud data; the third target area includes the second area to be spliced;

[0026] Controlling the second movable device to move out of the second area to be spliced;

[0027] Controlling the first movable device to collect point cloud data for the third target area again to obtain sixth point cloud data;

[0028] Determining an acquisition coordinate mapping relationship between the second position and the third position according to the fourth point cloud data, the fifth point cloud data, and the shape parameters of the three-dimensional reference object pre-configured;

[0029] Splicing the third point cloud data and the sixth point cloud data according to the acquisition coordinate mapping relationship.

[0030] In some possible implementation manners, the method further includes:

[0031] Obtaining first spliced data formed by splicing the first point cloud data and the fourth point cloud data, and obtaining second spliced data formed by splicing the third point cloud data and the sixth point cloud data;

[0032] Fusing the first spliced data and the second spliced data according to the correspondence between the third point cloud data and the fourth point cloud data, and removing the point information of the three-dimensional reference object in the second area to be spliced.

[0033] The present application also provides a tunnel point cloud data processing system, which includes a first movable device, a second movable device equipped with a preset stereo reference object, and a control device; the control device is used to implement the tunnel point cloud data processing method provided in the present application.

[0034] Compared with the prior art, this application has the following beneficial effects:

[0035] The tunnel point cloud data processing method provided in the present application realizes point cloud data collection for the tunnel through the cooperation of a first movable device for executing point cloud data collection and a second movable device equipped with a preset stereo reference object, and then splices the point cloud data according to the point cloud position information related to the stereo reference object in the collected point cloud data. The point cloud data can be spliced ​​more accurately and the spatial position relationship of the point cloud data segments with complete time can be retained. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A schematic diagram of the steps of the tunnel point cloud data processing method provided in this embodiment;

[0038] Figure 2 A schematic diagram of tunnel point cloud data collection provided in this embodiment;

[0039] Figure 3 One of the schematic diagrams of the tunnel point cloud data acquisition process provided in this embodiment;

[0040] Figure 4 One of the schematic diagrams of the three-dimensional reference object provided in this embodiment;

[0041] Figure 5 A second schematic diagram of a three-dimensional reference object provided for this embodiment;

[0042] Figure 6 The second schematic diagram of the tunnel point cloud data acquisition process provided in this embodiment;

[0043] Figure 7 The third schematic diagram of the tunnel point cloud data acquisition process provided in this embodiment;

[0044] Figure 8 A schematic diagram of a control device provided in this embodiment;

[0045] Fig. 9 A schematic diagram of the functional modules of the tunnel point cloud data processing device provided in this embodiment. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0047] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0048] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0049] In the description of the present application, it should be noted that the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0050] In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0051] The inventors have found that in existing tunnel point cloud data splicing solutions, the acquisition device itself usually records relative movement data for subsequent point cloud splicing, or uses point recognition and matching based on the point cloud data itself for splicing.

[0052] Among them, in the solution in which the acquisition device itself records the relative movement data, it is necessary to determine the relative relationship of the acquisition point coordinates when performing point cloud acquisition twice based on the movement data of the acquisition device, and then splice the point cloud data collected twice based on the relative relationship of the acquisition point coordinates. However, this method is highly dependent on the acquisition device accurately recording its own relative movement. Once a movement error occurs, the accuracy of point cloud splicing will be greatly affected. In addition, it is usually difficult to restore the slope information during the point cloud reconstruction process for tunnels with slopes.

[0053] In the solution of performing point recognition and matching based on the point cloud data itself for splicing, since the internal structure of the tunnel is usually simple and the similarities between different positions are relatively large, it is difficult to perform point recognition and matching between two point cloud data, and matching errors are prone to occur, affecting the subsequent splicing and restoration of point cloud data.

[0054] In view of this, the present embodiment provides a solution that can improve the reliability of laser point cloud data splicing in tunnel scenes. The solution provided by the present embodiment is described in detail below.

[0055] Please refer to Figure 1 , Figure 1 A flow chart of a tunnel point cloud data processing method provided in this embodiment is provided. The method including each step will be described in detail below.

[0056] Step S11, controlling the first movable device to move to a first position in the target tunnel, and collecting point cloud data of a first target area to obtain first point cloud data. The first target area includes a first area to be spliced.

[0057] In this embodiment, please refer to Figure 2 The first movable device 300 is configured with a laser point cloud acquisition component. The first movable device 300 can move in the target tunnel. When moving to a certain position, the first movable device 300 can emit a laser to the tunnel inner wall 400 near the position and obtain point cloud data of the tunnel inner wall 400 based on the laser reflected by the tunnel inner wall 400.

[0058] Step S12, controlling the second movable device carrying the preset three-dimensional reference object to move into the first area to be spliced ​​and then remain still.

[0059] In this embodiment, the second movable device includes another device that can move independently relative to the first movable device. The second movable device is equipped with a preset three-dimensional reference object. When the three-dimensional reference object is within the laser point cloud data collection range of the first movable device, it can form fixed-shape point data in the collected point cloud data.

[0060] In step S11, after the first movable device completes the first data collection of the first target area, the first movable device maintains the current position unchanged, and then controls the second movable device carrying the three-dimensional reference object to move into the data collection range of the first movable device.

[0061] For example, in this embodiment, the first movable device can perform point cloud data collection at least twice in sequence along the extension direction of the target tunnel. In this case, after completing the first data collection of the first target area in step S11, the second movable device can be controlled to move along the extension direction of the target tunnel to the edge of the first target area. This area is the area where the two areas need to be spliced ​​and partially overlap after the subsequent execution of point cloud data collection of the next area (hereinafter referred to as the second target area), that is, the aforementioned first area to be spliced.

[0062] Step S13: controlling the first movable device to collect point cloud data of the first target area again to obtain second point cloud data.

[0063] In this embodiment, please refer to Figure 3 Compared with the first point cloud data obtained in step S11, the second point cloud data obtained in step S13 includes the point information of the three-dimensional reference object located in the first area to be spliced.

[0064] Step S14, controlling the first movable device to move to a second position in the target tunnel, and collecting point cloud data of a second target area in the target tunnel to obtain third point cloud data; the second target area includes the first area to be spliced.

[0065] In this embodiment, the second target area may be an area along the extension direction of the tunnel, where the acquisition action is performed after the first target area in the point cloud data acquisition operation. The second target area partially overlaps with the first target area, and the overlapping area is the first area to be spliced.

[0066] In step S14, the first movable device may be controlled to move to the second position to collect data for the first time on the second target area while keeping the 3D reference object in the first area to be spliced, so as to obtain the third point cloud data. The third point cloud data includes the point information of the 3D reference object in the first area to be spliced.

[0067] Step S15, controlling the second movable device to move out of the first area to be spliced.

[0068] Step S16: controlling the first movable device to collect point cloud data of the second target area again to obtain fourth point cloud data.

[0069] Please refer again Figure 3 Compared with the third point cloud data obtained in step S14, in the fourth point cloud data obtained in step S16, there is no point position information of the three-dimensional reference object in the first area to be spliced.

[0070] Step S17, determining a collection coordinate mapping relationship between the first position and the second position according to the second point cloud data, the third point cloud data and the pre-configured shape parameters of the three-dimensional reference object.

[0071] In this embodiment, the second point cloud data is the point cloud data of the first target area collected at the first position, which includes the point information of the three-dimensional reference object located in the first area to be spliced, and the third point cloud data is the point cloud data of the second target area collected at the second position, which also includes the point information of the three-dimensional reference object located in the first area to be spliced. In addition, the three-dimensional reference object does not move in position and does not change in shape during these two scanning actions. Therefore, the acquisition coordinate mapping relationship between the first position and the second position can be determined based on the point information of the three-dimensional reference object in the second point cloud data and the third point cloud data.

[0072] Step S18: splicing the first point cloud data and the fourth point cloud data according to the acquisition coordinate mapping relationship.

[0073] In this embodiment, since the first point cloud data and the second point cloud data are both collected at the first position, and the third point cloud data and the fourth point cloud data are both collected at the second position, after the acquisition coordinate mapping relationship between the first position and the second position is determined in step S17, the first point cloud data and the fourth point cloud data can be spliced.

[0074] Among them, since the three-dimensional reference object does not appear in the first area to be spliced ​​in the first point cloud data and the fourth point cloud data, there is no point interference of the three-dimensional reference object in the point cloud data spliced ​​by the first point cloud data and the fourth point cloud data.

[0075] Based on the above analysis, the point cloud data collection of the tunnel is realized by the cooperation of the first movable device for executing point cloud data collection and the second movable device equipped with a preset stereo reference object, and then the point cloud data is spliced ​​according to the point cloud position information related to the stereo reference object in the collected point cloud data. Compared with the solution in the prior art in which the collection device records its own movement, the solution provided by this embodiment does not rely on the collection device to accurately record its own movement or turning, and can eliminate the interference of movement errors on point cloud splicing. Compared with the solution in the prior art that relies on the tunnel point cloud data itself for point matching, the solution provided by this embodiment adds a stereo reference object, which can effectively avoid the point matching error caused by the large similarity of various positions in the tunnel, and through the movement of the first movable device and the second movable device and multiple collection actions, the blocking interference of the stereo reference object on the tunnel point cloud data collection can be avoided.

[0076] In a possible implementation manner, in step S17, point information corresponding to the stereoscopic reference object may be determined from the second point cloud data and the third point cloud data respectively according to the shape parameters of the stereoscopic reference object.

[0077] The three-dimensional reference object can be an object that does not usually appear in a tunnel. For example, the three-dimensional reference object can be a regular tetrahedron. According to the shape characteristics of the regular tetrahedron, the point information corresponding to the three-dimensional reference object can be determined from the second point cloud data and the third point cloud data.

[0078] Then, based on the point information of the three-dimensional reference object in the second point cloud data and the third point cloud data, the second point cloud data and the third point cloud data are point aligned to obtain the acquisition coordinate mapping relationship between the first position and the second position.

[0079] Specifically, in this embodiment, since the position of the three-dimensional reference object does not change when the second point cloud data is collected at the first position and the third point cloud data is collected at the second position, and the shape parameters of the three-dimensional reference object can be determined in advance, the point information of the three-dimensional reference object in the second point cloud data and the third point cloud data is point matched and aligned to determine the acquisition coordinate mapping relationship between the first position and the second position.

[0080] Furthermore, after determining the point information corresponding to the stereoscopic reference object from the second point cloud data and the third point cloud data respectively according to the shape parameters of the stereoscopic reference object, it is also possible to first reconstruct and complete the points of the stereoscopic reference object in the second point cloud data and the third point cloud data that have not been collected, based on the point information corresponding to the stereoscopic reference object in the second point cloud data and the third point cloud data and the shape parameters of the stereoscopic reference object, to obtain the point information of the stereoscopic reference object after point reconstruction and completion.

[0081] Specifically, in the second point cloud data and the third point cloud data, due to different acquisition positions, each only includes the point information of the stereo reference object acquired from one direction. In order to improve the accuracy of subsequent point matching based on the point information of the stereo reference object, the positions where the stereo reference object is not acquired in the second point cloud data and the third point cloud data can be reconstructed and supplemented based on the known shape parameters of the stereo reference object, and then the second point cloud data and the third point cloud data are point aligned based on the supplemented point information to obtain the acquisition coordinate mapping relationship between the first position and the second position. In this way, the accuracy of the acquired acquisition coordinate mapping relationship can be further improved.

[0082] In some possible implementations, the first movable device includes a laser point cloud acquisition device that can move on the ground or on a ground track, for example, a mobile laser point cloud acquisition vehicle. The three-dimensional reference object includes a regular tetrahedron, and when the three-dimensional reference object is mounted on the second movable device, one cone angle faces downward. In this way, when the point information of the three-dimensional reference object is included in the acquisition range of the first movable device whose acquisition point is close to the ground, the occlusion of the point acquisition at other positions by a certain face of the three-dimensional reference object can be reduced, so that the first movable device can collect enough appearance details of the three-dimensional reference object, which is convenient for subsequent alignment processing according to the point information of the three-dimensional reference object.

[0083] Furthermore, in some possible implementations, the second movable device includes a horizontal tilt angle adjustment device, and the horizontal tilt angle adjustment device is used to keep the horizontal tilt angles of the three-dimensional reference object at different positions consistent.

[0084] Specifically, see Figure 4 If the second movable device is also a ground movable device, when the tunnel is inclined and extended, if the three-dimensional reference object is inclined along with the second movable device, the point position information of the three-dimensional reference object collected by the first movable acquisition device is the same as that when the tunnel is horizontally extended, and the spatial characteristics of the inclined tunnel will be lost during the subsequent point cloud splicing.

[0085] Therefore, please refer to Figure 5 In this embodiment, the horizontal inclination adjustment device can be set to keep the horizontal inclination of the three-dimensional reference object at different positions consistent, so that when the second movable device is tilted with the tunnel slope, the three-dimensional reference object can be unaffected. In this way, when the point cloud data collected at different positions are spliced ​​based on the point information of the three-dimensional reference object, the spatial characteristics of the tunnel tilt can be effectively reflected, and the accuracy of the point data splicing reconstruction can be improved.

[0086] In another possible implementation, the second movable device includes a drone. In step S12, the drone with a preset three-dimensional reference object fixedly mounted thereon may be controlled to move to the first area to be spliced ​​and hover at a fixed position.

[0087] In this way, the hovering and airborne drones are naturally not affected by the ground environment, and the horizontal inclination angles of the three-dimensional reference object at different positions can be kept consistent. In addition, the second movable device and the first movable device move on the ground and in the air respectively, which can reduce the mutual influence between the two devices and improve the efficiency of the mobile operation. For example, in a tunnel with only a one-way track on the ground, the second movable device flying in the air will not block the first movable device moving on the track.

[0088] In some possible implementations, the point density of the first point cloud data and the fourth point cloud data is greater than the point density of the second point cloud data and the third point cloud data.

[0089] In this way, after collecting the second point cloud data and the third point cloud data, the amount of data storage can be reduced, and when determining the acquisition coordinate mapping relationship, using point cloud data with lower density can reduce the amount of calculation for point matching. When performing point cloud splicing, using point cloud data with higher density can improve the accuracy of the spliced ​​point cloud data.

[0090] In some other possible implementations, the density of the point cloud data collected at each time may be the same.

[0091] In this case, see Figure 6 The second target area also includes a second area to be spliced, and the second area to be spliced ​​does not overlap with the first area to be spliced.

[0092] In step S15, the second movable device may be controlled to move from the first area to be spliced ​​to the second area to be spliced;

[0093] After step S18, the method provided in this embodiment may further include the following steps.

[0094] Step S19, controlling the first movable device to move to a third position in the target tunnel, and collecting point cloud data of a third target area in the target tunnel to obtain fifth point cloud data; the third target area includes the second area to be spliced.

[0095] Step S20, controlling the second movable device to move out of the second area to be spliced.

[0096] Step S21: Control the first movable device to collect point cloud data of the third target area again to obtain sixth point cloud data.

[0097] Step S22: determining a collection coordinate mapping relationship between the second position and the third position according to the fourth point cloud data, the fifth point cloud data and the pre-configured shape parameters of the three-dimensional reference object.

[0098] Step S23: splicing the third point cloud data and the sixth point cloud data according to the acquisition coordinate mapping relationship.

[0099] That is, after the second movable device is equipped with the three-dimensional reference object serving as a coordinate calibration reference for the first position and the second position, it can be moved to the second area to be stitched where the second target area and the third target area overlap, thereby completing the point cloud data stitching of the second target area and the third target area from a single coordinate calibration reference serving as the second position and the third position.

[0100] Furthermore, in some possible implementations, after step S23, the method provided in this embodiment may further include the following steps.

[0101] Step S24, obtaining first spliced ​​data formed by splicing the first point cloud data and the fourth point cloud data, and obtaining second spliced ​​data formed by splicing the third point cloud data and the sixth point cloud data.

[0102] Step S25: According to the correspondence between the third point cloud data and the fourth point cloud data, the first stitching data and the second stitching data are merged, and the point information of the three-dimensional reference object in the second area to be stitched is removed.

[0103] Specifically, see Figure 7 In the first spliced ​​data formed by splicing the first point cloud data and the fourth point cloud data, although there is no point interference of the stereo reference object in the first area to be spliced, there is still point interference of the stereo reference object in the second area to be spliced.

[0104] Therefore, the point data of the second area to be spliced ​​without the point interference of the stereo reference object in the second spliced ​​data spliced ​​by the third point cloud data and the sixth point cloud data can be fused and replaced, thereby removing the point information interference of the stereo reference object in the second area to be spliced. The third point cloud data and the fourth point cloud data are both point cloud data collected at the second position, so except for the points corresponding to the stereo reference object, the laser point information of other positions is the same.

[0105] By analogy, the first movable device and the second movable device move and cooperate alternately to collect data, so as to obtain point cloud data of various positions along the extension direction of the target tunnel, and through the splicing, fusion and replacement of the point cloud data, the point interference of the three-dimensional reference object in the point cloud data can be matched to obtain accurate laser point cloud data of the entire target tunnel.

[0106] It should be noted that in this embodiment, after completing the point cloud data collection of multiple target areas, the point cloud data splicing action can be performed uniformly, or after completing the point cloud data collection of two adjacent target areas, the point cloud data splicing action can be performed immediately, which is not specifically limited in this embodiment.

[0107] This embodiment also provides a tunnel point cloud data processing system, the system comprising a first movable device, a second movable device equipped with a preset stereoscopic reference object, and a control device. The control device is used to implement Figure 1 The tunnel point cloud data processing method shown.

[0108] The control device can implement information interaction with the first movable device and the second movable device through wireless communication or wired communication to control the first movable device and the second movable device to move or collect data.

[0109] In some possible implementations, the control device can remotely control the first movable device and / or the second movable device. In other possible implementations, the control device can be mounted on or integrated into the first movable device and / or the second movable device, so that the first movable device and / or the second movable device can be controlled from a short distance.

[0110] Please refer to Figure 8 , Figure 8 The control device 100 provided in this embodiment is a block diagram. The control device 100 includes a tunnel point cloud data processing device 110 , a machine-readable storage medium 120 , and a processor 130 .

[0111] The machine-readable storage medium 120, the processor 130 and the communication unit 140 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines. The tunnel point cloud data processing device 110 includes at least one software function module that can be stored in the machine-readable storage medium 120 in the form of software or firmware or solidified in the operating system (OS) of the control device 100. The processor 130 is used to execute the executable modules stored in the machine-readable storage medium 120, such as the software function modules and computer programs included in the tunnel point cloud data processing device 110.

[0112] The machine-readable storage medium 120 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc. The machine-readable storage medium 120 is used to store a program, and the processor 130 executes the program / executable tunnel point cloud data processing method provided in this embodiment after receiving an execution instruction.

[0113] The processor 130 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0114] Please refer to Fig. 9This embodiment further provides a tunnel point cloud data processing device 110, which includes at least one functional module that can be stored in a machine-readable storage medium 120 in the form of software. Functionally, the tunnel point cloud data processing device 110 may include a first acquisition control module 111, a first movement control module 112, a second acquisition control module 113, a third acquisition control module 114, a second movement control module 115, a fourth acquisition control module 116, a coordinate mapping processing module 117, and a point cloud data splicing module 118.

[0115] The first acquisition control module 111 is used to control the first movable device to move to a first position in the target tunnel, and to acquire point cloud data of a first target area to obtain first point cloud data. The first target area includes a first area to be spliced.

[0116] In this embodiment, the first acquisition control module 111 can be used to execute Figure 1 As shown in step S11, for the detailed description of the first acquisition control module 111, please refer to the description of step S11.

[0117] The first movement control module 112 is used to control the second movable device carrying the preset three-dimensional reference object to move to the first to-be-joined area and then remain stationary.

[0118] In this embodiment, the first movement control module 112 may be used to execute Figure 1 As shown in step S12, for a detailed description of the first movement control module 112, please refer to the description of step S12.

[0119] The second acquisition control module 113 is used to control the first movable device to collect point cloud data of the first target area again to obtain second point cloud data.

[0120] In this embodiment, the second acquisition control module 113 can be used to execute Figure 1 As shown in step S13, for the detailed description of the second acquisition control module 113, please refer to the description of step S13.

[0121] The third acquisition control module 114 is used to control the first movable device to move to a second position in the target tunnel, and to acquire point cloud data of a second target area in the target tunnel to obtain third point cloud data. The second target area includes the first area to be spliced.

[0122] In this embodiment, the third acquisition control module 114 can be used to execute Figure 1Step S14 shown above. For the specific description of the third acquisition control module 114, reference can be made to the description of Step S14.

[0123] The second movement control module 115 is used to control the second movable device to move out of the first area to be spliced.

[0124] In this embodiment, the second movement control module 115 can be used to execute Figure 1 Step S15 shown above. For the specific description of the second movement control module 115, reference can be made to the description of Step S15.

[0125] The fourth acquisition control module 116 is used to control the first movable device to perform point cloud data acquisition on the second target area again to obtain the fourth point cloud data.

[0126] In this embodiment, the fourth acquisition control module 116 can be used to execute Figure 1 Step S16 shown above. For the specific description of the fourth acquisition control module 116, reference can be made to the description of Step S16.

[0127] The coordinate mapping processing module 117 is used to determine the acquisition coordinate mapping relationship between the first position and the second position according to the second point cloud data, the third point cloud data, and the shape parameters of the pre-configured three-dimensional reference object.

[0128] In this embodiment, the coordinate mapping processing module 117 can be used to execute Figure 1 Step S17 shown above. For the specific description of the coordinate mapping processing module 117, reference can be made to the description of Step S17.

[0129] The point cloud data splicing module 118 is used to splice the first point cloud data and the fourth point cloud data according to the acquisition coordinate mapping relationship.

[0130] In this embodiment, the point cloud data splicing module 118 can be used to execute Figure 1 Step S18 shown above. For the specific description of the point cloud data splicing module 118, reference can be made to the description of Step S18.

[0131] In summary, for the tunnel point cloud data processing method provided in this application, the first movable device for performing point cloud data acquisition and the second movable device carrying a pre-set three-dimensional reference object cooperate to perform point cloud data acquisition on the tunnel, and then the point cloud data is spliced according to the point cloud position information related to the three-dimensional reference object in the collected point cloud data, so that the splicing of the point cloud data can be more accurately realized, and the spatial position relationship of the complete time of the point cloud data segment can be retained.

[0132] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code 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 box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0133] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0134] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0135] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0136] The above are only various implementations of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for processing tunnel point cloud data, characterized in that: The method comprises: Controlling a first movable device to move to a first position in a target tunnel, and collecting point cloud data of a first target area to obtain first point cloud data; the first target area includes a first area to be spliced; Controlling a second movable device carrying a preset three-dimensional reference object to move to the first area to be spliced ​​and then remain stationary; Controlling the first movable device to collect point cloud data of the first target area again to obtain second point cloud data; Controlling the first movable device to move to a second position in the target tunnel, and collecting point cloud data of a second target area in the target tunnel to obtain third point cloud data; the second target area includes the first area to be spliced; Controlling the second movable device to move out of the first area to be spliced; Controlling the first movable device to collect point cloud data of the second target area again to obtain fourth point cloud data; Determine a collection coordinate mapping relationship between the first position and the second position according to the second point cloud data, the third point cloud data and the pre-configured shape parameters of the three-dimensional reference object; wherein the second point cloud data and the third point cloud data contain point position information of the three-dimensional reference object and the second movable device located in the first area to be spliced; The first point cloud data and the fourth point cloud data are spliced ​​according to the acquisition coordinate mapping relationship; wherein the first point cloud data and the fourth point cloud data do not include the point position information of the three-dimensional reference object and the second movable device located in the first area to be spliced.

2. The method according to claim 1, characterized in that: The step of determining the acquisition coordinate mapping relationship between the first position and the second position according to the second point cloud data, the third point cloud data and the pre-configured shape parameters of the three-dimensional reference object comprises: Determining point information corresponding to the three-dimensional reference object from the second point cloud data and the third point cloud data respectively according to the shape parameters of the three-dimensional reference object; Based on the point information of the three-dimensional reference object in the second point cloud data and the third point cloud data, point alignment processing is performed on the second point cloud data and the third point cloud data to obtain a collection coordinate mapping relationship between the first position and the second position.

3. The method according to claim 2, characterized in that After the step of determining the point information corresponding to the three-dimensional reference object from the second point cloud data and the third point cloud data respectively according to the shape parameters of the three-dimensional reference object, the method further includes: According to the point information corresponding to the stereoscopic reference object in the second point cloud data and the third point cloud data and the shape parameters of the stereoscopic reference object, point reconstruction and completion are performed on the positions of the stereoscopic reference object in the second point cloud data and the third point cloud data that have not been collected to obtain the point information of the stereoscopic reference object after point reconstruction and completion.

4. The method according to claim 1, characterized in that: The first movable device comprises a laser point cloud acquisition device that can move on the ground or on a ground track; the three-dimensional reference object comprises a regular tetrahedron, and when the three-dimensional reference object is mounted on the second movable device, a cone angle of the three-dimensional reference object faces downward.

5. The method according to claim 1, characterized in that The second movable device comprises a horizontal tilt angle adjustment device, and the horizontal tilt angle adjustment device is used to keep the horizontal tilt angles of the three-dimensional reference object at different positions consistent.

6. The method according to claim 1, characterized in that The second movable device includes a drone; the step of controlling the second movable device carrying the preset three-dimensional reference object to move to the first area to be spliced ​​includes: A drone with a preset three-dimensional reference object fixedly mounted thereon is controlled to move to the first area to be spliced ​​and to hover at a fixed position.

7. The method according to claim 1, characterized in that The point density of the first point cloud data and the fourth point cloud data is greater than the point density of the second point cloud data and the third point cloud data.

8. The method according to claim 1, characterized in that The second target area also includes a second area to be spliced, and the second area to be spliced ​​does not overlap with the first area to be spliced; the step of controlling the second movable device to move out of the first area to be spliced ​​includes: Controlling the second movable device to move from the first area to be spliced ​​to the second area to be spliced; After the step of controlling the first movable device to collect point cloud data of the second target area again to obtain fourth point cloud data, the method further includes: Controlling the first movable device to move to a third position in the target tunnel, and collecting point cloud data of a third target area in the target tunnel to obtain fifth point cloud data; the third target area includes the second area to be spliced; Controlling the second movable device to move out of the second area to be spliced; Controlling the first movable device to collect point cloud data of the third target area again to obtain sixth point cloud data; Determine a collection coordinate mapping relationship between the second position and the third position according to the fourth point cloud data, the fifth point cloud data and the pre-configured shape parameters of the three-dimensional reference object; The third point cloud data and the sixth point cloud data are spliced ​​according to the acquisition coordinate mapping relationship.

9. The method according to claim 8, characterized in that The method further comprises: Obtaining first spliced ​​data formed by splicing the first point cloud data and the fourth point cloud data, and obtaining second spliced ​​data formed by splicing the third point cloud data and the sixth point cloud data; According to the correspondence between the third point cloud data and the fourth point cloud data, the first stitching data and the second stitching data are merged, and the point information of the three-dimensional reference object in the second area to be stitched is removed.

10. A tunnel point cloud data processing system, characterized in that: The system includes a first movable device, a second movable device equipped with a preset stereoscopic reference object, and a control device; the control device is used to implement the method described in any one of claims 1-9.

Images