Method and device for generating outdoor large-scale scene laser radar point cloud map

Abstract

The invention relates to the technical field of point cloud data processing, in particular to a method and device for generating an outdoor large-scale scene laser radar point cloud map, and the method comprises the steps: obtaining a preliminary segmentation result of a target laser radar point cloud map based on a region growth segmentation mode, and carrying out the optimization processing of boundary points, obtaining a target plane segmentation result of the point cloud map; calculating target normal vectors of all segmented planes in the target plane segmentation result, performing plane point cloud refinement processing on the plane segmentation result, performing plane segmentation on a point cloud map subjected to refinement processing, determining a target wall corner structure of a new target plane segmentation result, and removing target miscellaneous points in the wall corner point cloud of the wall corner structure to obtain a new wall corner structure; and a refined outdoor large-scale scene laser radar point cloud map is generated. Therefore, the problems that the point cloud precision cannot be increased from hardware and algorithm levels in a short time, data noise is increased, and the requirement for generating the point cloud map in a complex scene cannot be met in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of point cloud data processing, and in particular to a method and device for generating an outdoor large-scene laser radar point cloud map. Background Art

[0002] As a high-precision active sensor, LiDAR (Light Detection And Ranging) is widely used in 3D reconstruction tasks. However, due to the design defects of the LiDAR system and the errors of the 3D reconstruction algorithm itself, the generated 3D point cloud map often contains a lot of data noise, which is mainly manifested in large outdoor scenes where the outer walls of buildings are thick.

[0003] Since lidar point cloud maps are an important input for generating three-dimensional structural models, it is impossible to increase the point cloud accuracy from the hardware and algorithm levels in a short period of time, which increases data noise and cannot meet the needs of generating point cloud maps in complex scenarios, which urgently needs to be improved. Summary of the invention

[0004] The present invention provides a method and device for generating an outdoor large-scene laser radar point cloud map, so as to solve the problem in the related art that, since the laser radar point cloud map is an important input for generating a three-dimensional structure model, it is impossible to increase the point cloud accuracy from the hardware and algorithm levels in a short period of time, which increases the data noise and cannot meet the demand for generating point cloud maps in complex scenes.

[0005] The first aspect of the present invention provides a method for generating an outdoor large-scene lidar point cloud map, comprising the following steps: obtaining a preliminary segmentation result of a target lidar point cloud map based on a region growing segmentation method, and performing boundary point optimization processing on the preliminary segmentation result to obtain a target plane segmentation result of the point cloud map; calculating the target normal vectors of all segmentation planes in the target plane segmentation result, and using the target normal vectors to perform plane point cloud refinement processing on the plane segmentation result to generate a refined point cloud map; performing plane segmentation on the refined point cloud map to obtain a new target plane segmentation result, and determining the target corner structure of the new target plane segmentation result, and removing target noise in the corner point cloud of the corner structure to generate a refined outdoor large-scene lidar point cloud map.

[0006] Optionally, in one embodiment of the present invention, the region growing-based segmentation method obtains a preliminary segmentation result of the target lidar point cloud map, including: calculating the local normal vector of each scanning point in the target lidar point cloud map; based on the region growing segmentation method, performing point cloud clustering on the local normal vector of each scanning point to obtain the preliminary segmentation result of the target lidar point cloud map.

[0007] Optionally, in one embodiment of the present invention, the boundary point optimization processing of the preliminary segmentation result includes: calculating the vertical distance and the Euclidean distance from the non-planar point to the segmentation plane to obtain the non-planar point that meets the preset conditions; dividing the non-planar point that meets the preset conditions into the segmentation plane to perform boundary point optimization processing on the preliminary segmentation result.

[0008] Optionally, in one embodiment of the present invention, the plane segmentation result is subjected to plane point cloud refinement processing using the target normal vector to generate a refined point cloud map, including: calculating the domain center of gravity of the plane points in the segmentation plane; determining new plane points in the segmentation plane based on the plane points, the domain center of gravity and the target normal vector; and generating a refined point cloud map based on the new plane points.

[0009] Optionally, in one embodiment of the present invention, determining the target corner structure of the new target plane segmentation result and removing target noise in the corner point cloud of the corner structure to generate a refined outdoor large-scene lidar point cloud map includes: obtaining the target plane in the new target plane segmentation result; judging whether the target plane is the target corner structure; if the target plane is the target corner structure, removing the target noise in the corner point cloud to generate a refined outdoor large-scene lidar point cloud map.

[0010] The second aspect of the present invention provides a device for generating an outdoor large-scene laser radar point cloud map, including: an acquisition module, which is used to obtain a preliminary segmentation result of a target laser radar point cloud map based on a region growing segmentation method, and perform boundary point optimization processing on the preliminary segmentation result to obtain a target plane segmentation result of the point cloud map; a processing module, which is used to calculate the target normal vectors of all segmentation planes in the target plane segmentation result, and use the target normal vectors to perform plane point cloud refinement processing on the plane segmentation result to generate a refined point cloud map; a generation module, which is used to perform plane segmentation on the refined point cloud map to obtain a new target plane segmentation result, and determine the target corner structure of the new target plane segmentation result, and remove the target noise in the corner point cloud of the corner structure to generate a refined outdoor large-scene laser radar point cloud map.

[0011] Optionally, in one embodiment of the present invention, the acquisition module includes: a first calculation unit, used to calculate the local normal vector of each scanning point in the target lidar point cloud map; a first acquisition unit, used to perform point cloud clustering on the local normal vector of each scanning point based on the region growing segmentation method to obtain the preliminary segmentation result of the target lidar point cloud map.

[0012] Optionally, in one embodiment of the present invention, the acquisition module includes: a second calculation unit, used to calculate the vertical distance and Euclidean distance from the non-plane point to the segmentation plane to obtain the non-plane point that meets the preset conditions; a processing unit, used to divide the non-plane points that meet the preset conditions into the segmentation plane to perform boundary point optimization processing on the preliminary segmentation result.

[0013] Optionally, in one embodiment of the present invention, the processing module includes: a third calculation unit, used to calculate the domain center of gravity of the plane point in the segmentation plane; a determination unit, used to determine a new plane point in the segmentation plane based on the plane point, the domain center of gravity and the target normal vector; and a first generation unit, used to generate a refined point cloud map based on the new plane point.

[0014] Optionally, in one embodiment of the present invention, the generation module includes: a second acquisition unit, used to acquire the target plane in the new target plane segmentation result; a judgment unit, used to judge whether the target plane is the target corner structure; and a second generation unit, used to remove the target noise in the corner point cloud if the target plane is the target corner structure, so as to generate a refined outdoor large-scene lidar point cloud map.

[0015] An embodiment of the third aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for generating an outdoor large-scene lidar point cloud map as described in the above embodiment.

[0016] The fourth aspect of the present invention provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above method for generating an outdoor large-scene lidar point cloud map.

[0017] A fifth aspect of the present invention provides a computer program product, including a computer program, which, when executed, is used to implement the above method for generating an outdoor large-scene lidar point cloud map.

[0018] The embodiment of the present invention can obtain the preliminary segmentation result of the target laser radar point cloud map based on the segmentation method of regional growth, and perform boundary point optimization processing to obtain the target plane segmentation result of the point cloud map; calculate the target normal vectors of all segmentation planes in the target plane segmentation result, and then perform plane point cloud refinement processing on the plane segmentation result to perform plane segmentation on the refined point cloud map, and determine the target corner structure of the new target plane segmentation result, and remove the target noise in the corner point cloud of the corner structure to generate a refined outdoor large scene laser radar point cloud map, effectively reduce data noise, and meet the needs of generating point cloud maps in complex scenes. Therefore, the problem that the related technology cannot increase the point cloud accuracy from the hardware and algorithm level in a short time, increases data noise, and cannot meet the needs of generating point cloud maps in complex scenes is solved.

[0019] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which: Figure 1 A flowchart of a method for generating an outdoor large-scene laser radar point cloud map according to an embodiment of the present invention; Figure 2 A schematic diagram of the principle of a method for generating an outdoor large-scene laser radar point cloud map according to a specific embodiment of the present invention; Figure 3 A schematic diagram of a plane segmentation result based on region growing according to a specific embodiment of the present invention; Figure 4 A schematic diagram of a plane segmentation result based on region growing and boundary point optimization according to a specific embodiment of the present invention; Figure 5 A schematic diagram of a point cloud map before plane point cloud refinement according to a specific embodiment of the present invention; Figure 6 A schematic diagram of a point cloud map after a plane point cloud is refined according to a specific embodiment of the present invention; Figure 7 A schematic diagram of a point cloud map before detail optimization based on building structure regularization according to a specific embodiment of the present invention; Figure 8 A schematic diagram of a point cloud map after detail optimization based on building structure regularization according to a specific embodiment of the present invention; Fig. 9 A schematic diagram of the structure of a device for generating an outdoor large-scene laser radar point cloud map according to an embodiment of the present invention; Fig.10 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0022] The following describes the method and device for generating an outdoor large-scene laser radar point cloud map according to an embodiment of the present invention with reference to the accompanying drawings. In view of the problem that the related technology mentioned in the background technology center cannot increase the point cloud accuracy from the hardware and algorithm level in a short time, increases data noise, and cannot meet the needs of generating point cloud maps in complex scenes, the present invention provides a method for generating an outdoor large-scene laser radar point cloud map, in which the preliminary segmentation result of the target laser radar point cloud map can be obtained based on the segmentation method of regional growth, and the boundary point optimization processing is performed to obtain the target plane segmentation result of the point cloud map; the target normal vectors of all segmentation planes in the target plane segmentation result are calculated, and then the plane segmentation result is subjected to plane point cloud refinement processing, so as to perform plane segmentation on the refined point cloud map, and determine the target corner structure of the new target plane segmentation result, and remove the target clutter in the corner point cloud of the corner structure, so as to generate a refined outdoor large-scene laser radar point cloud map, effectively reduce data noise, and meet the needs of generating point cloud maps in complex scenes. Thus, the problem that the related technology cannot increase the point cloud accuracy from the hardware and algorithm level in a short time, increases data noise, and cannot meet the needs of generating point cloud maps in complex scenes is solved.

[0023] Specifically, Figure 1 A schematic diagram of a flow chart of a method for generating an outdoor large-scene lidar point cloud map provided in an embodiment of the present invention.

[0024] like Figure 1 As shown, the method for generating the outdoor large-scene laser radar point cloud map includes the following steps: In step S101, based on the region growing segmentation method, a preliminary segmentation result of the target lidar point cloud map is obtained, and the preliminary segmentation result is subjected to boundary point optimization processing to obtain a target plane segmentation result of the point cloud map.

[0025] It is understandable that the embodiment of the present invention can obtain the preliminary segmentation result of the target laser radar point cloud map based on the segmentation method of region growing, for example, Figure 2As shown, the red scanning point is a non-planar scanning point. The embodiment of the present invention can adopt a parallel computing strategy to calculate the local normal vector of each scanning point of the point cloud map, and then use a point cloud clustering method based on region growing to cluster the scanning points with similar local normal vectors to obtain a preliminary segmentation result of the outdoor large-scene lidar point cloud map. Then, the preliminary segmentation result can be subjected to boundary point optimization processing, that is, by calculating the vertical distance and Euclidean distance from the non-planar point to the segmentation plane, some non-planar points, such as the point cloud at the corner of the wall, are attributed to the segmentation plane to obtain the target plane segmentation result of the point cloud map, which effectively improves the feasibility of the refined outdoor large-scene lidar point cloud map.

[0026] Among them, in one embodiment of the present invention, a preliminary segmentation result of the target lidar point cloud map is obtained based on a region growing segmentation method, including: calculating the local normal vector of each scanning point in the target lidar point cloud map; based on a region growing segmentation method, the local normal vector of each scanning point is clustered into point clouds to obtain a preliminary segmentation result of the target lidar point cloud map.

[0027] In the actual implementation process, the embodiment of the present invention can first calculate the local normal vector of each scanning point in the laser radar point cloud map, and the calculation method is as follows:

[0028] in, is the current scan point, is the neighborhood scan point of the current scan point, is the total number of neighborhood points (usually set to 50), is the local normal vector of the scan point to be solved.

[0029] Next, the local normal vector of the scan point is used as input to perform point cloud clustering based on region growing. Here, the RegionGrown class of PCL is used for implementation. The specific parameter settings are as follows:

[0030] So you can get Figure 3 The plane segmentation result based on region growing is shown, in which the non-planar point clouds at the corners of the wall are correctly attributed to the corresponding segmentation planes, effectively improving the calculation efficiency, segmentation accuracy and quality, while reducing the impact of noise.

[0031] Optionally, in one embodiment of the present invention, the preliminary segmentation result is subjected to boundary point optimization processing, including: calculating the vertical distance and Euclidean distance from the non-planar point to the segmentation plane to obtain the non-planar point that meets the preset conditions; dividing the non-planar points that meet the preset conditions into the segmentation plane to perform boundary point optimization processing on the preliminary segmentation result.

[0032] As a possible implementation method, the embodiment of the present invention can process the scanning points at the corners of the wall that are not attributed to the plane, and for each non-planar scanning point , calculate it and other splitting planes through the following calculation formula The vertical distances are sorted and the first ten segmentation planes with the closest vertical distances are retained for subsequent processing. The calculation formula is as follows:

[0033] in, is the total number of neighborhood points, is the non-planar scanning point To plane The vertical distance is the local normal vector of the scan point to be solved.

[0034] For the first ten closest perpendicular distances to the splitting plane , calculated by the following formula Euclidean distances to ten planes:

[0035] in, is a non-planar scanning point, Non-planar scanning point To the plane among the ten planes The Euclidean distance of For plane plane point.

[0036] Will Belong to In the smallest splitting plane, the updated splitting plane can be obtained ,in, Figure 4 The plane segmentation result after boundary point optimization is displayed, so that the embodiment of the present invention can perform boundary point optimization processing on the preliminary segmentation result to obtain the target plane segmentation result of the point cloud map, thereby significantly improving the segmentation accuracy and quality of the point cloud map.

[0037] In step S102, the target normal vectors of all segmented planes in the target plane segmentation result are calculated, and the plane point cloud of the plane segmentation result is refined using the target normal vectors to generate a refined point cloud map.

[0038] It is understandable that the embodiment of the present invention can calculate the target normal vectors of all segmented planes in the target plane segmentation result, and use the target normal vectors to perform plane point cloud refinement processing on the plane segmentation result, for example, Figure 2As shown, the embodiment of the present invention can perform a field search on each plane point of the segmentation plane, and then calculate the center point of the field, compress the plane points along the plane normal toward the center of the field, thereby achieving the effect of thinning the plane, generating a refined point cloud map, and effectively reducing data noise.

[0039] Optionally, in one embodiment of the present invention, the plane segmentation result is subjected to plane point cloud refinement processing using a target normal vector to generate a refined point cloud map, including: calculating the domain center of gravity of the plane points in the segmentation plane; determining new plane points in the segmentation plane based on the plane points, the domain center of gravity and the target normal vector; and generating a refined point cloud map based on the new plane points.

[0040] In some embodiments, the present invention can update the segmentation plane obtained in the above steps. Perform plane point cloud refinement operations, for segmentation plane , first calculate its plane point according to the following formula Field focus ,Right now:

[0041] in, Set to 150.

[0042] Next, principal component analysis is used to calculate the segmentation plane The normal vector , and update the plane points according to the following formula ,Right now:

[0043] in, Plane Point The focus of the field, Split plane The normal vector of .

[0044] After performing the above operations on all the planar points of the segmented planes, the refinement of the planar point cloud based on the local normal is completed, as shown in Figure 5 and Figure 6 The following are the results of the LiDAR point cloud map before and after the local normal-based planar point cloud refinement.

[0045] In step S103, the refined point cloud map is plane segmented to obtain a new target plane segmentation result, and the target corner structure of the new target plane segmentation result is determined, and the target noise in the corner point cloud of the corner structure is removed to generate a refined outdoor large scene lidar point cloud map.

[0046] It is understandable that the embodiment of the present invention can perform plane segmentation on the refined point cloud map to obtain a new target plane segmentation result, and determine the target corner structure of the new target plane segmentation result, for example, Figure 2 As shown in the figure, based on the regularized detail optimization of the building structure, for the refined point cloud map, the plane segmentation of the above steps is first performed again to obtain a new target plane segmentation result. Then, the corner structure is determined by orthogonal check and Euclidean distance, and finally the corner point cloud clutter is identified and removed to generate a refined outdoor large-scene lidar point cloud map, which greatly improves the accuracy of equipment fusion mapping, reduces data noise, and meets the needs of generating refined point cloud maps in large outdoor scenes.

[0047] Optionally, in one embodiment of the present invention, the target corner structure of the new target plane segmentation result is determined, and the target noise in the corner point cloud of the corner structure is removed to generate a refined outdoor large-scene lidar point cloud map, including: obtaining the target plane in the new target plane segmentation result; judging whether the target plane is the target corner structure; if the target plane is the target corner structure, removing the target noise in the corner point cloud to generate a refined outdoor large-scene lidar point cloud map.

[0048] In some embodiments, the present invention first performs plane segmentation based on region growing and boundary point optimization again on the point cloud map after plane point cloud refinement to obtain a new plane segmentation result. , for the new plane segmentation result From all the planes in the image, two planes are extracted in turn, and whether they are corner structures is determined based on orthogonality and Euclidean distance. , search by For each plane in the and Orthogonality:

[0049] Sort by orthogonality and choose The first five smallest plane pairs are selected as candidate planes. , then calculate according to the following formula and The Euclidean distance of each plane in :

[0050] in, express and candidate planes In The Euclidean distance of express The plane point, is the number of plane points, For plane The plane point, is the number of plane points.

[0051] If you have the minimum Candidate planes With plane Orthogonality Less than a given threshold (here it is set to 0.17), then it is considered and Forming corner structure.

[0052] For each retrieved corner plane pair and , first regularize the building structure. Process each plane of the plane pair separately, and for one of the planes , according to the following rules, its plane points Regular set and negative point set :

[0053] in, Finger plane center of gravity.

[0054] First, the punctual set and negative point set The point set with more points is processed, assuming The number of points in the point set is large. Each point in is updated according to the following rules:

[0055] in, for Points in a concentration; To determine the distance threshold between a point and another plane, it is set to 0.2 meters here; The distance that a point in the point set moves to another plane is set to 0.1 meters here.

[0056] After completing the above operations on both planes of the corner plane pair, finally perform noise removal and update the plane pair. and For one of the planes, , still according to the following rule, the plane points are divided into regular point sets and negative point set :

[0057] Here we assume that the point set with a smaller number of points is ,Will The point set is regarded as a clutter set, and the points in it are removed from the point cloud map, that is, the detail tuning operation based on the regularization of the building structure is completed. Figure 7 and Figure 8 They are the point cloud maps before and after processing. Figure 7 This is the point cloud map before the detail optimization based on the regularization of the building structure. There are obvious gaps at the corners of the wall. Figure 8 The point cloud map is fine-tuned based on the details of the building structure regularization, and the gaps at the corners of the walls are filled.

[0058] According to the method for generating an outdoor large-scene laser radar point cloud map proposed in an embodiment of the present invention, a preliminary segmentation result of a target laser radar point cloud map can be obtained based on a segmentation method of regional growth, and boundary point optimization processing can be performed to obtain a target plane segmentation result of the point cloud map; the target normal vectors of all segmentation planes in the target plane segmentation result are calculated, and then the plane point cloud is refined for the plane segmentation result, so as to perform plane segmentation on the refined point cloud map, and determine the target corner structure of the new target plane segmentation result, and remove the target noise in the corner point cloud of the corner structure, so as to generate a refined outdoor large-scene laser radar point cloud map, effectively reduce data noise, and meet the needs of generating point cloud maps in complex scenes. Thus, the problem that the related art cannot increase the point cloud accuracy from the hardware and algorithm level in a short time, increases data noise, and cannot meet the needs of generating point cloud maps in complex scenes is solved.

[0059] Next, a device for generating an outdoor large-scene lidar point cloud map according to an embodiment of the present invention is described with reference to the accompanying drawings.

[0060] Fig. 9 It is a block diagram of a device for generating an outdoor large-scene lidar point cloud map according to an embodiment of the present invention.

[0061] like Fig. 9 As shown, the device 10 for generating an outdoor large-scene lidar point cloud map includes: an acquisition module 100, a processing module 200 and a generation module 300.

[0062] Specifically, the acquisition module 100 is used to obtain the preliminary segmentation result of the target lidar point cloud map based on the region growing segmentation method, and perform boundary point optimization processing on the preliminary segmentation result to obtain the target plane segmentation result of the point cloud map.

[0063] The processing module 200 is used to calculate the target normal vectors of all segmentation planes in the target plane segmentation result, and use the target normal vectors to perform plane point cloud refinement processing on the plane segmentation result to generate a refined point cloud map.

[0064] The generation module 300 is used to perform plane segmentation on the refined point cloud map to obtain a new target plane segmentation result, determine the target corner structure of the new target plane segmentation result, and remove the target noise in the corner point cloud of the corner structure to generate a refined outdoor large-scene lidar point cloud map.

[0065] Optionally, in one embodiment of the present invention, the acquisition module 100 includes: a first calculation unit and a first acquisition unit.

[0066] Among them, the first calculation unit is used to calculate the local normal vector of each scanning point in the target lidar point cloud map.

[0067] The first acquisition unit is used to perform point cloud clustering on the local normal vector of each scanning point based on the region growing segmentation method to obtain the preliminary segmentation result of the target laser radar point cloud map.

[0068] Optionally, in one embodiment of the present invention, the acquisition module 100 includes: a second calculation unit and a processing unit.

[0069] The second calculation unit is used to calculate the vertical distance and the Euclidean distance from the non-planar point to the segmentation plane to obtain the non-planar point that meets the preset conditions.

[0070] The processing unit is used to divide the non-planar points that meet the preset conditions into the segmentation plane to perform boundary point optimization processing on the preliminary segmentation result.

[0071] Optionally, in one embodiment of the present invention, the processing module 200 includes: a third calculating unit, a determining unit and a first generating unit.

[0072] The third calculation unit is used to calculate the center of gravity of the plane points in the segmentation plane.

[0073] The determination unit is used to determine a new plane point in the segmentation plane based on the plane point, the center of gravity of the region and the target normal vector.

[0074] The first generating unit is used to generate a refined point cloud map according to the new plane points.

[0075] Optionally, in one embodiment of the present invention, the generating module 300 includes: a second acquiring unit, a judging unit and a second generating unit.

[0076] The second acquisition unit is used to acquire the target plane in the new target plane segmentation result.

[0077] The judging unit is used to judge whether the target plane is a target corner structure.

[0078] The second generating unit is used to remove target noise in the corner point cloud if the target plane is a target corner structure, so as to generate a refined outdoor large-scene lidar point cloud map.

[0079] It should be noted that the aforementioned explanation of the embodiment of the method for generating a large-scale outdoor scene lidar point cloud map is also applicable to the device for generating a large-scale outdoor scene lidar point cloud map of this embodiment, and will not be repeated here.

[0080] According to the device for generating an outdoor large-scene laser radar point cloud map proposed in an embodiment of the present invention, the preliminary segmentation result of the target laser radar point cloud map can be obtained based on the segmentation method of regional growth, and the boundary point optimization processing can be performed to obtain the target plane segmentation result of the point cloud map; the target normal vectors of all segmentation planes in the target plane segmentation result are calculated, and then the plane point cloud is refined for the plane segmentation result, so as to perform plane segmentation on the refined point cloud map, and determine the target corner structure of the new target plane segmentation result, and remove the target noise in the corner point cloud of the corner structure, so as to generate a refined outdoor large-scene laser radar point cloud map, effectively reduce data noise, and meet the needs of generating point cloud maps in complex scenes. Thus, the problem that the related technology cannot increase the point cloud accuracy from the hardware and algorithm level in a short time, increases data noise, and cannot meet the needs of generating point cloud maps in complex scenes is solved.

[0081] Fig.10 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device may include: A memory 1001 , a processor 1002 , and a computer program stored in the memory 1001 and executable on the processor 1002 .

[0082] When the processor 1002 executes the program, the method for generating an outdoor large-scene lidar point cloud map provided in the above embodiment is implemented.

[0083] Furthermore, the electronic device further comprises: The communication interface 1003 is used for communication between the memory 1001 and the processor 1002 .

[0084] The memory 1001 is used to store computer programs that can be executed on the processor 1002 .

[0085] The memory 1001 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0086] If the memory 1001, the processor 1002 and the communication interface 1003 are implemented independently, the communication interface 1003, the memory 1001 and the processor 1002 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.10 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0087] Optionally, in a specific implementation, if the memory 1001, the processor 1002 and the communication interface 1003 are integrated on a chip, the memory 1001, the processor 1002 and the communication interface 1003 can communicate with each other through an internal interface.

[0088] The processor 1002 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0089] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method for generating an outdoor large-scene lidar point cloud map as described above is implemented.

[0090] This embodiment also provides a computer program product, including a computer program, which, when executed, is used to implement the above method for generating an outdoor large-scene lidar point cloud map.

[0091] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0092] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0093] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0094] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0095] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0096] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0097] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0098] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for generating an outdoor large-scene laser radar point cloud map, characterized in that: The following steps are involved: Based on the segmentation method of region growing, a preliminary segmentation result of the target lidar point cloud map is obtained, and the boundary point optimization processing is performed on the preliminary segmentation result to obtain a target plane segmentation result of the point cloud map; Calculating target normal vectors of all segmentation planes in the target plane segmentation result, and performing plane point cloud refinement processing on the plane segmentation result using the target normal vectors to generate a refined point cloud map; The refined point cloud map is plane segmented to obtain a new target plane segmentation result, and the target corner structure of the new target plane segmentation result is determined, and the target noise in the corner point cloud of the corner structure is removed to generate a refined outdoor large-scene lidar point cloud map.

2. The method for generating an outdoor large-scene laser radar point cloud map according to claim 1, characterized in that: The segmentation method based on region growing is used to obtain the preliminary segmentation result of the target laser radar point cloud map, including: Calculate the local normal vector of each scanning point in the target laser radar point cloud map; Based on the region growing segmentation method, the local normal vector of each scanning point is clustered into point clouds to obtain the preliminary segmentation result of the target lidar point cloud map.

3. The method for generating an outdoor large-scene laser radar point cloud map according to claim 1, characterized in that: The performing boundary point optimization processing on the preliminary segmentation result includes: Calculating the vertical distance and the Euclidean distance from the non-planar point to the segmentation plane to obtain the non-planar point that meets the preset conditions; The non-planar points that meet the preset conditions are divided into the segmentation plane to perform boundary point optimization processing on the preliminary segmentation result.

4. The method for generating an outdoor large-scene laser radar point cloud map according to claim 1, characterized in that: The using the target normal vector to perform plane point cloud refinement processing on the plane segmentation result to generate a refined point cloud map includes: Calculate the centroid of the area of ​​the plane point in the segmentation plane; Determining a new plane point in the segmentation plane based on the plane point, the field center of gravity and the target normal vector; A refined point cloud map is generated based on the new plane points.

5. The method for generating an outdoor large-scene laser radar point cloud map according to claim 1, characterized in that: The step of determining the target corner structure of the new target plane segmentation result and removing target clutter in the corner point cloud of the corner structure to generate a refined outdoor large-scene laser radar point cloud map includes: Obtaining a target plane in the new target plane segmentation result; Determining whether the target plane is the target corner structure; If the target plane is the target corner structure, the target clutter in the corner point cloud is removed to generate a refined outdoor large-scene lidar point cloud map.

6. A device for generating outdoor large-scene laser radar point cloud map, characterized in that: include: An acquisition module is used to acquire a preliminary segmentation result of a target laser radar point cloud map based on a region growing segmentation method, and to perform boundary point optimization processing on the preliminary segmentation result to obtain a target plane segmentation result of the point cloud map; A processing module, used for calculating target normal vectors of all segmentation planes in the target plane segmentation result, and performing plane point cloud refinement processing on the plane segmentation result using the target normal vectors to generate a refined point cloud map; A generation module is used to perform plane segmentation on the refined point cloud map to obtain a new target plane segmentation result, determine the target corner structure of the new target plane segmentation result, and remove target noise in the corner point cloud of the corner structure to generate a refined outdoor large-scene lidar point cloud map.

7. The device for generating an outdoor large-scene laser radar point cloud map according to claim 6, characterized in that: The acquisition module comprises: A calculation unit, used to calculate the local normal vector of each scanning point in the target laser radar point cloud map; An acquisition unit is used to perform point cloud clustering on the local normal vector of each scanning point based on the region growing segmentation method to obtain the preliminary segmentation result of the target lidar point cloud map.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for generating an outdoor large-scene lidar point cloud map as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the method for generating an outdoor large-scene lidar point cloud map as described in any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that The computer program is executed by a processor to implement the method for generating an outdoor large-scene lidar point cloud map as described in any one of claims 1 to 5.

Images