Map construction method, device, electronic device and storage medium

Abstract

The present application relates to a map construction method, device, electronic device and storage medium, which are applied to the field of autonomous driving technology. The method comprises: obtaining a first normal distribution transformation map pre-constructed based on an original point cloud map, wherein the resolution of the first normal distribution transformation map is greater than a resolution threshold; obtaining a target resolution, wherein the target resolution is the resolution of the map to be constructed, and the target resolution is less than the resolution of the first normal distribution transformation map; based on the voxel information of each voxel grid in the first normal distribution transformation map and the target resolution, obtaining a second normal distribution transformation map with a resolution of the target resolution. The present application can reduce storage consumption and computational complexity.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a map construction method, device, electronic device and storage medium. Background Art

[0002] In the field of autonomous driving technology, it is necessary to build a priori maps in advance when doing radar map matching. In related technologies, point cloud maps of different resolutions can be directly constructed using the original point cloud map. However, since the original point cloud map requires more storage space, the hardware storage capacity of the vehicle-side device is required to be high. In addition, when generating NDT (Normal Distributions Transform) maps of different resolutions, it is necessary to traverse all the original point clouds to complete the calculation of the mean and covariance of the point cloud within the voxel, and the calculation complexity is relatively high. Summary of the invention

[0003] In order to solve the above technical problems, the present application provides a map construction method, device, electronic device and storage medium.

[0004] According to a first aspect of the present application, a map construction method is provided, comprising:

[0005] Acquire a first normal distribution transformation map pre-constructed based on the original point cloud map, wherein a resolution of the first normal distribution transformation map is greater than a resolution threshold;

[0006] Acquire a target resolution, wherein the target resolution is a resolution of a map to be constructed, and the target resolution is smaller than a resolution of the first normal distribution transformation map;

[0007] Based on the voxel information of each voxel grid in the first normal distribution transformation map and the target resolution, a second normal distribution transformation map with a resolution of the target resolution is obtained.

[0008] Optionally, obtaining a second normal distribution transformation map having a resolution of the target resolution based on the voxel information of each voxel grid in the first normal distribution transformation map and the target resolution includes:

[0009] Determine index information of each voxel grid in the first normal distribution transformation map according to the centroid in the voxel information of each voxel grid and the target resolution;

[0010] Divide the voxel grids with the same index information into the same target voxel grid, and determine the voxel information of the target voxel grid according to the voxel information of the voxel grids with the same index information;

[0011] A second normal distribution transformation map having a resolution equal to the target resolution is constructed according to the voxel information of all target voxel grids.

[0012] Optionally, determining the index information of each voxel grid according to the centroid in the voxel information of each voxel grid in the first normal distribution transformation map and the target resolution includes:

[0013] Dividing the position coordinates of the centroid of each voxel grid in the first normal distribution transformation map by the target resolution to obtain a target value corresponding to each voxel grid;

[0014] If the target value is a positive number, the target value is rounded down to obtain index information of each voxel grid;

[0015] If the target value is a negative number, the target value is rounded up to obtain the index information of each voxel grid.

[0016] Optionally, the voxel information of each voxel grid includes: the number of point clouds contained in each voxel grid, the centroid and covariance of the voxel grid;

[0017] The step of determining the voxel information of the target voxel grid according to the voxel information of the voxel grids having the same index information includes:

[0018] The sum of the number of point clouds contained in the voxel grids with the same index information is used as the number of point clouds contained in the target voxel;

[0019] Taking the average value of the position coordinates of the centroids of the voxel grids with the same index information as the position coordinates of the centroid of the target voxel grid;

[0020] The covariance of the target voxel grid is determined according to the position coordinates of the centroid of the voxel grid with the same index information and the position coordinates of the centroid of the target voxel grid.

[0021] Optionally, before obtaining the first normal distribution transformation map pre-constructed based on the original point cloud map, the method further includes:

[0022] Get the original point cloud map;

[0023] Perform a normal distribution transformation on the original point cloud map to obtain the first normal distribution transformed map.

[0024] According to a second aspect of the present application, a map construction device is provided, comprising:

[0025] A first normal distribution transformation map acquisition module is used to acquire a first normal distribution transformation map pre-constructed based on the original point cloud map, wherein the resolution of the first normal distribution transformation map is greater than a resolution threshold;

[0026] A target resolution acquisition module, used to acquire a target resolution, wherein the target resolution is a resolution of a map to be constructed, and the target resolution is smaller than a resolution of the first normal distribution transformation map;

[0027] The second normal distribution transformation map construction module is used to obtain a second normal distribution transformation map with a resolution of the target resolution based on the voxel information of each voxel grid in the first normal distribution transformation map and the target resolution.

[0028] Optionally, the second normal distribution transformation map construction module is specifically used to determine the index information of each voxel grid according to the center of mass in the voxel information of each voxel grid in the first normal distribution transformation map and the target resolution; divide the voxel grids with the same index information into the same target voxel grid, and determine the voxel information of the target voxel grid according to the voxel information of the voxel grids with the same index information; and construct a second normal distribution transformation map with a resolution of the target resolution according to the voxel information of all target voxel grids.

[0029] Optionally, the second normal distribution transformation map construction module is specifically used to determine the index information of each voxel grid according to the centroid in the voxel information of each voxel grid in the first normal distribution transformation map and the target resolution through the following steps:

[0030] Dividing the position coordinates of the centroid of each voxel grid in the first normal distribution transformation map by the target resolution to obtain a target value corresponding to each voxel grid;

[0031] If the target value is a positive number, the target value is rounded down to obtain index information of each voxel grid;

[0032] If the target value is a negative number, the target value is rounded up to obtain the index information of each voxel grid.

[0033] Optionally, the voxel information of each voxel grid includes: the number of point clouds contained in each voxel grid, the centroid and covariance of the voxel grid;

[0034] The second normal distribution transformation map construction module is specifically used to determine the voxel information of the target voxel grid according to the voxel information of the voxel grid with the same index information through the following steps:

[0035] The sum of the number of point clouds contained in the voxel grids with the same index information is used as the number of point clouds contained in the target voxel;

[0036] Taking the average value of the position coordinates of the centroids of the voxel grids with the same index information as the position coordinates of the centroid of the target voxel grid;

[0037] The covariance of the target voxel grid is determined according to the position coordinates of the centroid of the voxel grid with the same index information and the position coordinates of the centroid of the target voxel grid.

[0038] Optionally, the map construction device further includes:

[0039] The original point cloud map acquisition module is used to obtain the original point cloud map;

[0040] The normal distribution transformation module is used to perform a normal distribution transformation on the original point cloud map to obtain the first normal distribution transformation map.

[0041] According to a third aspect of the present application, an electronic device is provided, comprising: a processor, wherein the processor is configured to execute a computer program stored in a memory, wherein the computer program implements the method described in the first aspect when executed by the processor.

[0042] According to a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first aspect is implemented.

[0043] According to a fifth aspect of the present application, a computer program product is provided. When the computer program product is run on a computer, the computer is enabled to execute the method described in the first aspect.

[0044] Compared with the prior art, the technical solution provided by the embodiments of the present application has the following advantages:

[0045] By pre-generating a first normal distribution transformation map with a resolution greater than a resolution threshold, i.e., a high-resolution NDT map, then directly based on the high-resolution NDT map and the resolution of the map to be constructed (i.e., the target resolution), a second normal distribution transformation map with a resolution of the target resolution is quickly generated. Since the target resolution is lower than the resolution of the first normal distribution transformation map, the second normal distribution transformation map is a low-resolution NDT map compared to the first normal distribution transformation map. In the embodiment of the present application, a low-resolution NDT map is constructed directly based on the high-resolution NDT map, and the original point cloud map is not used. The original point cloud map needs to occupy a large storage space. Therefore, it does not need to occupy a large storage space, and the vehicle-side device does not need to have a high hardware storage capacity. In addition, since the original point cloud map is not used, it is not necessary to traverse all the original point cloud maps to complete the calculation of the mean and covariance within the voxel, but it is sufficient to traverse all the voxels in the first normal distribution transformation map, which reduces the complexity of the algorithm and improves the calculation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0048] Figure 1 A flowchart of a map construction method in an embodiment of the present application;

[0049] Figure 2 A schematic diagram of the structure of a map construction device in an embodiment of the present application;

[0050] Figure 3 A schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present application, rather than all of the embodiments.

[0053] See also Figure 1 , Figure 1 A flowchart of a map construction method in an embodiment of the present application may include the following steps:

[0054] Step S110, obtaining a first normal distribution transformation map pre-constructed based on the original point cloud map.

[0055] Since the original point cloud map needs to occupy a large storage space, a first normal distribution transformation map can be constructed in advance based on the original point cloud map, wherein the resolution of the first normal distribution transformation map is greater than the resolution threshold. That is, the first normal distribution transformation map is a high-resolution NDT map. In this way, when a low-resolution NDT map needs to be constructed, it can be constructed directly based on the first normal distribution transformation map, and avoid using the original point cloud map for construction.

[0056] The method for constructing the first normal distribution transformation map can be: obtaining the original point cloud map, performing a normal distribution transformation on the original point cloud map, and obtaining the first normal distribution transformation map. That is, the space where the original point cloud map is located is divided into a grid of units, namely a voxel grid. The voxel grid is a pixel in a 3D space, a quantized, fixed-size point cloud. The voxel information of the voxel grid includes the number of point clouds contained in the voxel grid, the centroid of the voxel grid (that is, the average value of the position coordinates of the point clouds contained in the voxel grid) and the covariance.

[0057] Step S120, obtaining the target resolution.

[0058] In the embodiment of the present application, when constructing the NDT map, a corresponding resolution can be set, and the corresponding NDT map can be constructed by acquiring the resolution. The target resolution is the resolution of the map to be constructed. Since the map to be constructed is generated based on the first normal distribution transformation map, the target resolution is smaller than the resolution of the first normal distribution transformation map.

[0059] Step S130 , based on the voxel information of each voxel grid in the first normal distribution transformation map and the target resolution, a second normal distribution transformation map having a resolution equal to the target resolution is obtained.

[0060] It can be understood that the higher the resolution, the smaller the voxel grid, and the lower the resolution, the larger the voxel grid. Therefore, when constructing a low-resolution NDT map based on a high-resolution NDT map, the voxel grid in the high-resolution NDT map contained in each voxel grid in the low-resolution NDT map to be constructed can be searched, and the low-resolution NDT map can be constructed based on the voxel grid in the high-resolution NDT map found.

[0061] In some embodiments, the index information of each voxel grid in the first normal distribution transformation map can be calculated, and the voxel grid of the high-resolution NDT map located in the voxel grid of the low-resolution NDT map can be searched according to the index information. The index information of each voxel grid can be determined according to the centroid and target resolution in the voxel information of each voxel grid in the first normal distribution transformation map. Optionally, the position coordinates of the centroid of each voxel grid in the first normal distribution transformation map can be divided by the target resolution to obtain the target value corresponding to each voxel grid; if the target value is a positive number, the target value is rounded down to obtain the index information of each voxel grid; if the target value is a negative number, the target value is rounded up to obtain the index information of each voxel grid.

[0062] If the index information of two voxel grids is the same, it indicates that the two voxel grids are located in the same voxel grid of the low-resolution NDT map, that is, the voxel grid of the high-resolution NDT map located in the voxel grid of the ground-resolution NDT map is found, and the voxel grids with the same index information can be divided into the same target voxel grid. The target voxel grid refers to the voxel grid of the low-resolution NDT map, and one index information corresponds to one target voxel grid.

[0063] Afterwards, the voxel information of the target voxel grid is determined based on the voxel information of the voxel grids with the same index information. The voxel information of each voxel grid includes: the number of point clouds contained in each voxel grid, the center of mass of the voxel grid, and the covariance. For each target voxel grid, the sum of the number of point clouds contained in the voxel grids with the same index information can be used as the number of point clouds contained in the target voxel; the average value of the position coordinates of the center of mass of the voxel grids with the same index information can be used as the position coordinates of the center of mass of the target voxel grid; the covariance of the target voxel grid is determined based on the position coordinates of the center of mass of the voxel grids with the same index information and the position coordinates of the center of mass of the target voxel grid. In the above manner, the voxel information of all target voxel grids can be determined.

[0064] According to the voxel information of all target voxel grids, a second normal distribution transformation map with a resolution of the target resolution is constructed. After the second normal distribution transformation map is constructed, the second normal distribution transformation map can also be visualized.

[0065] The map construction method of the embodiment of the present application is to pre-generate a first normal distribution transformation map with a resolution greater than a resolution threshold, that is, a high-resolution NDT map, and then directly generate a second normal distribution transformation map with a resolution of the target resolution based on the high-resolution NDT map and the resolution of the map to be constructed (that is, the target resolution). Since the target resolution is lower than the resolution of the first normal distribution transformation map, the second normal distribution transformation map belongs to a low-resolution NDT map compared with the first normal distribution transformation map. In the embodiment of the present application, a low-resolution NDT map is directly constructed based on the high-resolution NDT map, and the original point cloud map is not used. The original point cloud map needs to occupy a large storage space. Therefore, it does not need to occupy a large storage space, and the vehicle-side device does not need to have a high hardware storage capacity. In addition, since the original point cloud map is not used, it is not necessary to traverse all the original point cloud maps to complete the calculation of the mean and covariance within the voxel, but it is sufficient to traverse all the voxels in the first normal distribution transformation map, which reduces the complexity of the algorithm and improves the calculation efficiency.

[0066] Corresponding to the above method embodiment, the present application also provides a map construction device, see Figure 2 , the map construction device 200 includes:

[0067] A first normal distribution transformation map acquisition module 210 is used to acquire a first normal distribution transformation map pre-constructed based on the original point cloud map, wherein the resolution of the first normal distribution transformation map is greater than a resolution threshold;

[0068] A target resolution acquisition module 220, used to acquire a target resolution, wherein the target resolution is a resolution of a map to be constructed, and the target resolution is smaller than a resolution of the first normal distribution transformation map;

[0069] The second normal distribution transformation map construction module 230 is used to obtain a second normal distribution transformation map with a resolution of the target resolution based on the voxel information of each voxel grid in the first normal distribution transformation map and the target resolution.

[0070] Optionally, the second normal distribution transformation map construction module 230 is specifically used to determine the index information of each voxel grid based on the center of mass and target resolution in the voxel information of each voxel grid in the first normal distribution transformation map; divide the voxel grids with the same index information into the same target voxel grid, and determine the voxel information of the target voxel grid based on the voxel information of the voxel grids with the same index information; and construct a second normal distribution transformation map with a resolution of the target resolution based on the voxel information of all target voxel grids.

[0071] Optionally, the second normal distribution transformation map construction module 230 is specifically configured to determine the index information of each voxel grid according to the centroid and target resolution in the voxel information of each voxel grid in the first normal distribution transformation map through the following steps:

[0072] Divide the position coordinates of the centroid of each voxel grid in the first normal distribution transformation map by the target resolution to obtain a target value corresponding to each voxel grid;

[0073] If the target value is a positive number, round it down to get the index information of each voxel grid;

[0074] If the target value is negative, round it up to get the index information of each voxel grid.

[0075] Optionally, the voxel information of each voxel grid includes: the number of point clouds contained in each voxel grid, the centroid and covariance of the voxel grid;

[0076] The second normal distribution transformation map construction module 230 is specifically used to determine the voxel information of the target voxel grid according to the voxel information of the voxel grid with the same index information through the following steps:

[0077] The sum of the number of point clouds contained in the voxel grid with the same index information is taken as the number of point clouds contained in the target voxel;

[0078] The average value of the position coordinates of the centroids of the voxel grids with the same index information is used as the position coordinates of the centroid of the target voxel grid;

[0079] The covariance of the target voxel grid is determined according to the position coordinates of the centroid of the voxel grid with the same index information and the position coordinates of the centroid of the target voxel grid.

[0080] Optionally, the map construction device further includes:

[0081] The original point cloud map acquisition module is used to obtain the original point cloud map;

[0082] The normal distribution transformation module is used to perform a normal distribution transformation on the original point cloud map to obtain a first normal distribution transformation map.

[0083] The specific details of each module or unit in the above device have been described in detail in the corresponding method, so they will not be repeated here.

[0084] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0085] In an exemplary embodiment of the present application, an electronic device is further provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the above-mentioned map construction method in this exemplary embodiment.

[0086] Figure 3 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. It should be noted that: Figure 3 The electronic device 300 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0087] like Figure 3 As shown, electronic device 300 includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage part 308 into a random access memory (RAM) 303. In RAM 303, various programs and data required for system operation are also stored. Central processing unit 301, ROM 302 and RAM 303 are connected to each other via a bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0088] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a local area network (LAN) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0089] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit 301, various functions defined in the device of the present application are executed.

[0090] In an embodiment of the present application, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned map construction method is implemented.

[0091] It should be noted that the computer-readable storage medium shown in the present application may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, radio frequency, etc., or any suitable combination of the above.

[0092] In an embodiment of the present application, a computer program product is also provided. When the computer program product is run on a computer, the computer executes the above-mentioned map construction method.

[0093] It should be noted that, in this article, relational terms such as "first" and "second" 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.

[0094] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A map construction method, characterized in that: include: Acquire a first normal distribution transformation map pre-constructed based on the original point cloud map, wherein a resolution of the first normal distribution transformation map is greater than a resolution threshold; Acquire a target resolution, wherein the target resolution is a resolution of a map to be constructed, and the target resolution is smaller than a resolution of the first normal distribution transformation map; Determine index information of each voxel grid in the first normal distribution transformation map according to the centroid in the voxel information of each voxel grid and the target resolution; Divide the voxel grids with the same index information into the same target voxel grid, and determine the voxel information of the target voxel grid according to the voxel information of the voxel grids with the same index information; A second normal distribution transformation map having a resolution equal to the target resolution is constructed according to the voxel information of all target voxel grids.

2. The method according to claim 1, characterized in that The step of determining index information of each voxel grid according to the centroid in the voxel information of each voxel grid in the first normal distribution transformation map and the target resolution comprises: Dividing the position coordinates of the centroid of each voxel grid in the first normal distribution transformation map by the target resolution to obtain a target value corresponding to each voxel grid; If the target value is a positive number, the target value is rounded down to obtain index information of each voxel grid; If the target value is a negative number, the target value is rounded up to obtain the index information of each voxel grid.

3. The method according to claim 1, characterized in that The voxel information of each voxel grid includes: the number of point clouds contained in each voxel grid, the centroid and covariance of the voxel grid; The step of determining the voxel information of the target voxel grid according to the voxel information of the voxel grids having the same index information includes: The sum of the number of point clouds contained in the voxel grids with the same index information is used as the number of point clouds contained in the target voxel; Taking the average value of the position coordinates of the centroids of the voxel grids with the same index information as the position coordinates of the centroid of the target voxel grid; The covariance of the target voxel grid is determined according to the position coordinates of the centroid of the voxel grid with the same index information and the position coordinates of the centroid of the target voxel grid.

4. The method according to claim 1, characterized in that: Before obtaining the first normal distribution transformation map pre-constructed based on the original point cloud map, the method further includes: Get the original point cloud map; Perform a normal distribution transformation on the original point cloud map to obtain the first normal distribution transformed map.

5. A map construction device, characterized in that: The device comprises: A first normal distribution transformation map acquisition module is used to acquire a first normal distribution transformation map pre-constructed based on the original point cloud map, wherein the resolution of the first normal distribution transformation map is greater than a resolution threshold; A target resolution acquisition module, used to acquire a target resolution, wherein the target resolution is a resolution of a map to be constructed, and the target resolution is smaller than a resolution of the first normal distribution transformation map; The second normal distribution transformation map construction module is used to determine the index information of each voxel grid according to the center of mass in the voxel information of each voxel grid in the first normal distribution transformation map and the target resolution; divide the voxel grids with the same index information into the same target voxel grid, and determine the voxel information of the target voxel grid according to the voxel information of the voxel grids with the same index information; and construct a second normal distribution transformation map with a resolution of the target resolution according to the voxel information of all target voxel grids.

6. The device according to claim 5, characterized in that The second normal distribution transformation map construction module is specifically used to: determine the index information of each voxel grid according to the center of mass in the voxel information of each voxel grid in the first normal distribution transformation map and the target resolution: Dividing the position coordinates of the centroid of each voxel grid in the first normal distribution transformation map by the target resolution to obtain a target value corresponding to each voxel grid; If the target value is a positive number, the target value is rounded down to obtain index information of each voxel grid; If the target value is a negative number, the target value is rounded up to obtain the index information of each voxel grid.

7. An electronic device, characterized in that: include: A processor, wherein the processor is used to execute a computer program stored in a memory, wherein the computer program, when executed by the processor, implements the method according to any one of claims 1 to 4.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images