Obstacle clustering method, device, electronic device and storage medium

Abstract

The present application provides an obstacle clustering method, device, electronic device and storage medium. The electronic device constructs a spatial search grid through target spatial point information; and determines at least one target spatial search grid from the target spatial search grid through spatial clustering conditions to achieve the purpose of clustering the spatial point information. Since a large amount of spatial point information is divided by constructing a spatial search grid, and a single spatial grid is used as a processing target, compared with the method of directly processing a single spatial point information, the amount of calculation can be reduced to achieve an improvement in clustering efficiency.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to an obstacle clustering method, device, electronic device and storage medium. Background Art

[0002] When detecting obstacles through detection devices, a large number of point sets on the obstacle surface will generate a large amount of point cloud data. Since the acquired point cloud data is itself disordered, it is necessary to cluster it to separate individual obstacles.

[0003] At present, the main solutions used are machine learning models. However, due to the large amount of point cloud data itself and the complex calculation of the machine learning model itself, there is a problem of poor efficiency when clustering point cloud data to separate single obstacles. Summary of the invention

[0004] In order to overcome at least one of the shortcomings of the prior art, one of the purposes of the present application is to provide an obstacle clustering method, which is applied to an electronic device, and the method includes:

[0005] Acquire target spatial point information, wherein the target spatial point information belongs to any one of the spatial point information; each of the spatial point information represents a spatial position information of an obstacle to be confirmed;

[0006] Determine at least one target space search grid from the space search grids constructed based on the target space point information, wherein the space search grid represents a space range in the same reference system as the obstacle to be confirmed, the at least one target space search grid can constitute a space region without gaps, and the number of space point information in each of the target space search grids reaches a number threshold;

[0007] All the target space search grids are used as spatial clustering information for characterizing target obstacles; the target obstacles belong to the obstacles to be confirmed.

[0008] Optionally, determining at least one target space search grid from constructing a space search grid based on the target space point information includes:

[0009] Constructing a grid to be confirmed containing the target spatial point information;

[0010] Determine whether the number of spatial point information included in the to-be-confirmed grid reaches a number threshold;

[0011] If yes, the to-be-confirmed grid is used as the target space search grid;

[0012] If not, return to execute the step of obtaining the target space point information.

[0013] Optionally, the obstacle clustering method further includes:

[0014] Obtaining a neighboring grid to be confirmed that has an adjacent relationship with the target space search grid;

[0015] Determine whether the number of spatial point information included in the neighboring to-be-confirmed grid reaches the number threshold;

[0016] If yes, the neighboring grid to be confirmed is used as a new target space search grid.

[0017] Optionally, before obtaining the neighboring to-be-confirmed grid having an adjacent relationship with the target space search grid, the method further includes:

[0018] Determining whether a search queue is empty, the search queue being used to maintain the target space search grid;

[0019] If not, the target space search grid in the search queue is extracted, and the target space search grid is deleted from the search queue.

[0020] Optionally, after taking the to-be-confirmed grid as the target space search grid, the method further comprises:

[0021] The grid to be confirmed is written into the search queue as the target space search grid.

[0022] Optionally, after taking the to-be-confirmed grid as the target space search grid, the obstacle clustering method further includes:

[0023] The spatial point information included in the target space search grid is used as the spatial point information of the target obstacle and written into an obstacle list, wherein the obstacle list is used to maintain the spatial point information representing the target obstacle.

[0024] Optionally, the using all the target space search grids as spatial clustering information for characterizing target obstacles includes:

[0025] If the search queue is empty, the spatial point information contained in the obstacle list is used as the spatial clustering information for characterizing the target obstacle.

[0026] Optionally, acquiring target space point information includes:

[0027] Get point cloud dataset;

[0028] Determine whether the point cloud data set is empty;

[0029] If not, any spatial point information in the point cloud data set is used as the target spatial point information.

[0030] A second object of an embodiment of the present application is to provide an obstacle clustering device, which is applied to an electronic device, and the obstacle clustering device includes an information acquisition module, an information processing module, and a result output module;

[0031] The information acquisition module is used to acquire target spatial point information, and the target spatial point information belongs to any one of the spatial point information; each of the spatial point information represents a spatial position information of the obstacle to be confirmed;

[0032] The information processing module is used to determine at least one target space search grid from the space search grids constructed based on the target space point information, the space search grid represents the spatial range in the same reference system as the obstacle to be confirmed, the at least one target space search grid can constitute a space area without gaps, and the number of space point information in each of the target space search grids reaches a number threshold;

[0033] The result output module is used to use all the target space search grids as spatial clustering information for characterizing target obstacles; the target obstacles belong to the obstacles to be confirmed.

[0034] The third objective of an embodiment of the present application is to provide an electronic device, which includes a processor and a memory, wherein the memory stores computer-executable instructions, and when the computer-executable instructions are executed by the processor, the obstacle clustering method is implemented.

[0035] A fourth objective of an embodiment of the present application is to provide a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the obstacle clustering method is implemented.

[0036] Compared with the prior art, this application has the following beneficial effects:

[0037] The embodiments of the present application provide an obstacle clustering method, device, electronic device and storage medium. The electronic device constructs a spatial search grid through target spatial point information; and determines at least one target spatial search grid from the target spatial search grid through spatial clustering conditions to achieve the purpose of clustering the spatial point information. Since a large amount of spatial point information is divided by constructing a spatial search grid, and a single spatial grid is used as the processing target, compared with the method of directly processing a single spatial point information, the amount of calculation can be reduced to achieve the improvement of clustering efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] 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.

[0039] Figure 1 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0040] Figure 2 One of the step flow diagrams of the obstacle clustering method provided in the embodiment of the present application;

[0041] Figure 3 The second step flow diagram of the obstacle clustering method provided in the embodiment of the present application;

[0042] Figure 4 A schematic diagram of a grid to be confirmed provided in an embodiment of the present application;

[0043] Figure 5 The third step flow diagram of the obstacle clustering method provided in the embodiment of the present application;

[0044] Figure 6 A schematic diagram of a neighboring domain to be confirmed grid provided in an embodiment of the present application;

[0045] Figure 7 A poetic picture of the structure of the obstacle clustering device provided in an embodiment of the present application.

[0046] Icons: 120 - memory; 130 - processor; 210 - second grid to be confirmed; 200 - first grid to be confirmed; 300 - target space search grid; 310 - adjacent domain grid to be confirmed; 1101 - information acquisition module; 1102 - information processing module; 1103 - result output module. DETAILED DESCRIPTION

[0047] 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.

[0048] 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.

[0049] 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.

[0050] In the related art, the point cloud data obtained by the detection device is mainly clustered and separated through a pre-trained machine learning model to obtain the point cloud data sets generated by different obstacles.

[0051] However, considering that machine learning models need to perform a lot of calculations when processing data, and the amount of calculation increases exponentially with the scale of machine learning models. At the same time, point cloud data is generated from a large number of point sets on the surface of obstacles, so the massive amount of point cloud data further increases the amount of calculation. In addition, the higher the accuracy of the detection device, the larger the amount of corresponding point cloud data.

[0052] At present, there are many types of detection devices for obtaining point cloud data. The following uses laser radar as an example to illustrate the method of generating point cloud data. Obviously, the implementation method of the embodiment of the present application can also be applied to point cloud data obtained by other detection devices, and it does not need to make a creative contribution based on the technical solution disclosed in the present application.

[0053] When a laser beam hits the surface of an obstacle, the reflected laser will carry information such as direction and distance. If the laser beam is scanned along a specific trajectory, the spatial information and / or color information of the detected part of the obstacle will be obtained from the reflected laser signal during the scanning process. Therefore, the spatial information and / or color information of a large number of points on the surface of the obstacle can be obtained, and then point cloud data is formed. And as the accuracy of the laser radar increases, the amount of point cloud data will also increase accordingly, and then a lot of calculations will be required during processing.

[0054] In view of this, an embodiment of the present application provides an obstacle clustering method, which is applied to an electronic device, wherein the electronic device may be a detection device capable of acquiring point cloud data, or may be a server, a smart phone, a personal computer (PC), or other professional data processing equipment.

[0055] Please refer to Figure 1 The electronic device shown is a schematic diagram of the structure of the electronic device, which includes a memory 120 and a processor 130.

[0056] The memory 120 and the processor 130 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 processor 130 is used to execute executable modules stored in the memory 120. For example, the software function module included in the obstacle clustering device. When the software function module included in the obstacle clustering device is processed and executed, the above-mentioned obstacle clustering method is implemented.

[0057] The memory 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 memory 120 is used to store programs.

[0058] 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.

[0059] For the above obstacle clustering method, the following is combined with Figure 2 The steps of the method are described in detail in the flowchart shown in FIG. Figure 2 As shown, the obstacle clustering method performed by the electronic device includes:

[0060] Step S1000, obtaining target space point information.

[0061] The target spatial point information belongs to any one of the spatial point information; each spatial point information represents a spatial position information of an obstacle to be confirmed.

[0062] That is, in the embodiment of the present application, the spatial point information may be the coordinate information of each point on the obstacle surface in the spatial region determined based on the preset reference coordinate system. The multiple coordinate information on the obstacle surface can reflect the spatial position of the obstacle in the spatial region. As a possible example, the spatial point information may be obtained from the coordinate information in the point cloud data.

[0063] Step S1001: determining at least one target space search grid from the space search grids constructed based on the target space point information.

[0064] Among them, the spatial search grid represents the spatial range in the same reference system as the obstacle to be confirmed, at least one target spatial search grid can form a space area without gaps, and the number of spatial point information in each target spatial search grid reaches the number threshold.

[0065] It is worth noting that, since the spatial point information represents the spatial position information of the obstacle in the spatial area, and the obstacle usually occupies a certain spatial area, the spatial search grid also needs to be a three-dimensional area, and the three-dimensional area can fill the space in an arrangement method that is compatible with the shape of the three-dimensional area, so that there is no residual gap in the filled spatial area. As a possible implementation method, the spatial search grid can be one of a regular tetrahedron, a regular hexahedron, and a regular octahedron. Those skilled in the art can make an adaptive selection based on the requirements for grid accuracy.

[0066] Step S1009: using all target space search grids as spatial clustering information for characterizing target obstacles.

[0067] The target obstacle belongs to the obstacles to be confirmed in the spatial area. Since the target spatial search grid constitutes a spatial area without gaps, the spatial area without gaps corresponds to an obstacle. Therefore, the spatial point information in the target spatial search grid is used as the spatial clustering information of the target obstacle. Exemplarily, if the spatial point information is point cloud data, the spatial clustering information is the point cloud data of the target obstacle.

[0068] In the embodiment of the present application, the electronic device takes the spatial search grids that meet the spatial clustering conditions as target spatial search grids based on the spatial search grids constructed above, and classifies them into one category.

[0069] That is, the spatial point information in the target space search grid corresponds to an independent obstacle in the spatial region, thereby achieving the purpose of clustering the spatial point information corresponding to relatively independent obstacles in the spatial region to determine the spatial point information corresponding to at least one obstacle.

[0070] Based on the above obstacle clustering method, the electronic device constructs a spatial search grid through target spatial point information, and determines at least one target spatial search grid from the target spatial point information through spatial clustering conditions, thereby achieving the purpose of clustering the spatial point information. Since a large amount of spatial point information is divided by constructing a spatial search grid, and a single spatial grid is used as the processing target, compared with the method of directly processing a single spatial point information, the amount of calculation can be reduced to achieve the improvement of clustering efficiency.

[0071] As a possible example of spatial point information, the following takes a point cloud dataset as an example to exemplify step S1000. Figure 3 , step S1000 performed by the electronic device includes:

[0072] Step S1000-1, obtaining a point cloud data set.

[0073] Step S1000 - 2 , determining whether the point cloud dataset is empty.

[0074] Step S1000 - 3 , if not, taking any spatial point information in the point cloud data set as the target spatial point information.

[0075] Based on the above steps of the obstacle clustering method, the electronic device constructs a spatial search grid to cluster the point cloud data only after acquiring the point cloud data.

[0076] In the embodiment of the present application, since it is necessary to construct a spatial search grid for clustering spatial point information, constructing a search grid in the area corresponding to the spatial point information can improve the efficiency of determining the target spatial search grid. In view of this, please refer again to Figure 3 , step S1001 includes:

[0077] Step S1001-1, constructing a grid to be confirmed containing target spatial point information.

[0078] Step S1001-2, determining whether the number of spatial point information included in the grid to be confirmed reaches a number threshold.

[0079] The number threshold is related to the size of the grid to be confirmed and the density of the spatial point information. Those skilled in the art can make adaptive adjustments based on the preset size of the grid to be confirmed and the density of the spatial point information. For example, when the size of the grid to be confirmed is small and the density of the spatial point information is also small, the number threshold can be set to a smaller value; similarly, if the size of the grid to be confirmed is large and the density of the spatial point information is also large, the number threshold can be set to a larger value.

[0080] Step S1001-3: If yes, the grid to be confirmed is used as the target space search grid.

[0081] If not, the electronic device returns to the step of acquiring target space point information until the target space search grid is determined.

[0082] It is worth noting that the spatial point information is relatively evenly distributed in space, and the electronic device selects the target spatial point information from the spatial point information based on a preset selection rule, and constructs a grid to be confirmed based on the target spatial point information. Since the selected target spatial point information is uncertain, it may be necessary to repeat the selection multiple times to determine the target spatial search grid that meets the number threshold.

[0083] Among them, if the grid to be confirmed is located inside the spatial area where the obstacle is located, the spatial point information in the grid to be confirmed is greater than the number threshold. On the contrary, if the grid to be confirmed is not located inside the spatial area where the obstacle is located (for example, located at the edge of the spatial area where the obstacle is located), the spatial point information in the grid to be confirmed is not greater than the number threshold. Therefore, based on this feature, the spatial point information located within the boundary of a single obstacle, that is, the spatial point information within the target space search grid can be determined from a large amount of spatial point information through the number threshold.

[0084] In view of the relationship between the above-mentioned to-be-confirmed grids and the number threshold, the following is combined with Figure 4 An example is given. Figure 4 The multiple spatial point information shown represents the spatial area where an obstacle is located in the spatial area. As shown in Figure 4, the first grid to be confirmed 200 and the second grid to be confirmed 210. Among them, the first grid to be confirmed 200 is located inside the spatial area where the obstacle is located, and the second grid to be unconfirmed is located at the edge of the interior of the spatial area where the obstacle is located. Therefore, the spatial point information in the first grid to be confirmed 200 is significantly more than the spatial point information in the second grid to be confirmed 210. Then the electronic device uses the first grid to be confirmed 200 as the target spatial search grid.

[0085] In the embodiment of the present application, considering that the determined target space search grid is located inside the space region where the obstacle is located, that is, a single target space search grid can only represent a local area of ​​the space region where a single obstacle is located. In order to determine all spatial point information within the boundary of a single obstacle, in the implementation of the present application, the electronic device constructs adjacent neighboring grids to be confirmed through the determined target space search grid, and continuously expands to the surroundings until the entire obstacle area is traversed.

[0086] In view of this, please refer to Figure 5 , the obstacle clustering method also includes the steps of:

[0087] Step S1005: obtaining a neighboring grid to be confirmed that has an adjacent relationship with the target space search grid.

[0088] Step S1007, determining whether the number of spatial point information included in the neighboring to-be-confirmed grid reaches a number threshold.

[0089] Step S1008: If yes, the neighboring grid to be confirmed is used as a new target space search grid.

[0090] Through the above steps of the obstacle clustering method, the electronic device can also construct adjacent neighboring grids to be confirmed based on the target space search grid, and find out whether there are neighboring grids to be confirmed that meet the number threshold and use them as new target space search grids.

[0091] Since the neighboring grid to be confirmed is constructed based on the target space search grid, once the electronic device determines a new target space search grid based on the number threshold, it continues to construct a new neighboring grid to be confirmed with the new target space search grid until all target space search grids in the space area corresponding to the spatial point information are traversed. Therefore, through the above steps, the electronic device can at least determine one target space search grid.

[0092] Considering that the spatial search grid can have different three-dimensional shapes, the following takes a regular hexahedron as an example, combined with Figure 6 , an exemplary description is given of a method of constructing a neighboring area to be confirmed grid 310. The neighboring area to be confirmed grid 310 has the same shape as the target space search grid 300.

[0093] like Figure 6 As shown, the electronic device searches for a target space based on a grid 300 ( Figure 6 The six faces of the target space search grid 300 (the dashed line part in the middle) are used to construct a neighboring unconfirmed grid 310 which is also a regular hexahedron; and it is determined whether the spatial point information in the neighboring unconfirmed grid 310 reaches the number threshold, and the neighboring unconfirmed grid 310 that reaches the number threshold is used as the new target space search grid 300, and the neighboring unconfirmed grid 310 adjacent to the new target space search grid 300 is continued to be constructed.

[0094] In the implementation of this application, it is necessary to construct adjacent neighboring grids to be confirmed through the target space search grid, considering that there may be multiple target space search grids. Therefore, as a possible implementation method, the search queue is used to maintain the target space search grid in the implementation of this application. After the electronic device selects the target space search grid from the search queue, it is necessary to delete the selected target space search grid from the search queue to keep the target space search grid in the search queue unprocessed.

[0095] In view of this, based on this search queue, please refer to Figure 5 After step S1001, the obstacle clustering method performed by the electronic device further includes:

[0096] Step, S1002, the electronic device writes the to-be-confirmed grids that have reached a number threshold into a search queue as target space search grids.

[0097] Accordingly, based on this search queue, please refer again to Figure 6 Before step S1007, the obstacle clustering method further includes:

[0098] Step S1003, determining whether the search queue is empty.

[0099] Step S1004: if not, extract the target space search grid in the search queue, and delete the target space search grid from the search queue.

[0100] That is, in the embodiment of the present application, the electronic device provides a search queue for recording and maintaining the traversed target space search grid.

[0101] In order to maintain the spatial point information satisfying the spatial clustering condition, the electronic device may provide an obstacle list for recording the spatial point information in the target spatial search grid.

[0102] Therefore, please refer again to Figure 5 After step S1004, the obstacle clustering method performed by the electronic device further includes:

[0103] Step S1006: The spatial point information included in the target spatial search grid is used as the spatial point information of the target obstacle and written into the obstacle list.

[0104] The obstacle list is used to maintain the spatial point information representing the target obstacles.

[0105] In the embodiment of the present application, the electronic book device determines whether the search queue is empty to determine whether it is necessary to continue to construct adjacent neighboring grids to be confirmed with the target space search grid. When the search queue is empty, it means that the electronic device has clustered the spatial point information representing a target obstacle from the spatial point information.

[0106] Therefore, please refer again to Figure 5 In the obstacle clustering method performed by the electronic device, step S1009 includes:

[0107] Step S1009-1: If the search queue is empty, the spatial point information contained in the obstacle list is used as spatial clustering information for characterizing the target obstacle.

[0108] Based on the same invention concept, please refer to Figure 7This embodiment further provides an obstacle clustering device, which includes at least one functional module that can be stored in a memory in the form of software. From a functional perspective, the obstacle clustering device may include:

[0109] The information acquisition module 1101 is used to acquire target spatial point information, where the target spatial point information belongs to any one of the spatial point information; each spatial point information represents a spatial position information of an obstacle to be confirmed.

[0110] In the embodiment of the present application, when the computer executable instructions corresponding to the information acquisition module are executed by the processor, Figure 2 For a detailed description of step S1000 in the information acquisition module, please refer to the detailed description of step S100.

[0111] The information processing module 1102 is used to determine at least one target space search grid from the space search grids constructed based on the target space point information.

[0112] Among them, the spatial search grid represents the spatial range in the same reference system as the obstacle to be confirmed, at least one target spatial search grid can form a space area without gaps, and the number of spatial point information in each target spatial search grid reaches the number threshold.

[0113] In the embodiment of the present application, when the computer executable instructions corresponding to the information processing module are executed by the processor, Figure 2 For a detailed description of the information processing module, please refer to the detailed description of step S1001.

[0114] The result output module 1103 is used to use all target space search grids as spatial clustering information for characterizing target obstacles; the target obstacles belong to obstacles to be confirmed.

[0115] In the embodiment of the present application, when the computer executable instructions corresponding to the information acquisition module are executed by the processor, Figure 2 For a detailed description of the information acquisition module, please refer to the detailed description of step S1009.

[0116] In addition, it is worth noting that the above-mentioned information acquisition module 1101, information processing module 1102 and result output module 1103 in the embodiment of the present application can also be used to implement other steps or sub-steps of the above-mentioned obstacle clustering method, and the embodiment of the present application does not make specific limitations.

[0117] An embodiment of the present application further provides an electronic device, which includes a processor and a memory, wherein the memory stores computer executable instructions, and when the computer executable instructions are executed by the processor, the above obstacle clustering method is implemented.

[0118] The embodiment of the present application further provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the above obstacle clustering method is implemented.

[0119] In summary, the embodiments of the present application provide an obstacle clustering method, device, electronic device, and storage medium. The electronic device constructs a spatial search grid through target spatial point information; and determines at least one target spatial search grid therefrom through spatial clustering conditions to achieve the purpose of clustering spatial point information. Since a large amount of spatial point information is segmented by constructing a spatial search grid, and a single spatial grid is used as the processing target, compared with the method of directly processing a single spatial point information, the amount of calculation can be reduced to achieve an improvement in clustering efficiency.

[0120] 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.

[0121] 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.

[0122] If the functions are implemented in the form of software function modules and sold or used as independent products, they 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, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0123] 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.

[0124] 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. An obstacle clustering method, characterized in that: Applied to electronic equipment, the method comprises: Get the target space point information, including: Acquire a point cloud data set through a laser radar; and determine whether the point cloud data set is empty; If not, any spatial point information in the point cloud data set is used as the target spatial point information, wherein the spatial point information is obtained from the coordinate information in the point cloud data, and each of the spatial point information represents a spatial position information of the obstacle to be confirmed; Determine at least one target space search grid from the space search grids constructed based on the target space point information, wherein the space search grid is a three-dimensional area, representing a spatial range in the same reference system as the obstacle to be confirmed, and the at least one target space search grid can constitute a space area without gaps, and the number of space point information in each of the target space search grids reaches a number threshold; All the target space search grids are used as spatial clustering information for characterizing target obstacles; the target obstacles belong to the obstacles to be confirmed.

2. The obstacle clustering method according to claim 1, characterized in that: Determining at least one target space search grid from constructing a space search grid based on the target space point information includes: Constructing a grid to be confirmed containing the target spatial point information; Determine whether the number of spatial point information included in the to-be-confirmed grid reaches the number threshold; If yes, the to-be-confirmed grid is used as the target space search grid; If not, return to execute the step of obtaining the target space point information.

3. The obstacle clustering method according to claim 2, characterized in that: The obstacle clustering method further includes: Obtaining a neighboring grid to be confirmed that has an adjacent relationship with the target space search grid; Determine whether the number of spatial point information included in the neighboring to-be-confirmed grid reaches the number threshold; If yes, the neighboring grid to be confirmed is used as a new target space search grid.

4. The obstacle clustering method according to claim 3, characterized in that: Before obtaining the neighboring to-be-confirmed grid having an adjacent relationship with the target space search grid, the method further includes: Determining whether a search queue is empty, the search queue being used to maintain the target space search grid; If not, the target space search grid in the search queue is extracted, and the target space search grid is deleted from the search queue.

5. The obstacle clustering method according to claim 4, characterized in that: After the to-be-confirmed grid is used as the target space search grid, the method includes: The grid to be confirmed is written into the search queue as the target space search grid.

6. The obstacle clustering method according to claim 4, characterized in that: After taking the to-be-confirmed grid as the target space search grid, the obstacle clustering method further includes: The spatial point information included in the target space search grid is used as the spatial point information of the target obstacle and written into an obstacle list, wherein the obstacle list is used to maintain the spatial point information representing the target obstacle.

7. The obstacle clustering method according to claim 6, characterized in that: The using all the target space search grids as spatial clustering information for characterizing target obstacles includes: If the search queue is empty, the spatial point information contained in the obstacle list is used as the spatial clustering information for characterizing the target obstacle.

8. An obstacle clustering device, characterized in that: Applied to electronic equipment, the obstacle clustering device includes an information acquisition module, an information processing module and a result output module; The information acquisition module is used to acquire target space point information, including: Acquire a point cloud data set through a laser radar; and determine whether the point cloud data set is empty; If not, any spatial point information in the point cloud data set is used as the target spatial point information, wherein the spatial point information is obtained from the coordinate information in the point cloud data; each of the spatial point information represents a spatial position information of the obstacle to be confirmed; The information processing module is used to determine at least one target space search grid from the space search grids constructed based on the target space point information, the space search grid is a three-dimensional area, representing the space range in the same reference system as the obstacle to be confirmed, the at least one target space search grid can constitute a space area without gaps, and whether the number of space point information in each of the target space search grids reaches a number threshold; The result output module is further used to use all the target space search grids as spatial clustering information for characterizing a target obstacle; the target obstacle belongs to the obstacle to be confirmed.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores computer executable instructions, and when the computer executable instructions are executed by the processor, the obstacle clustering method according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the obstacle clustering method according to any one of claims 1 to 7 is implemented.

Images