Method and apparatus for obtaining position of hinge and computer device

Abstract

The invention discloses a method and equipment for obtaining the position of a hinge, a computer device and a storage medium. Specifically, disclosed is a method for obtaining a position of a hinge, comprising: obtaining 3D data of an environment in which a hinge is located and converting the 3D data of the environment into 2D data; determining a 2D position of the grab bucket in the 2D data according to a boundary frame of the grab bucket; obtaining a 3D space of the grab bucket according to the 2D position of the grab bucket; the 3D space of the hinge is determined according to the 3D space of the grab bucket; and determining a 3D position of the hinge in the 3D data of the environment according to the 3D space of the hinge. In this way, the position of the hinge can be accurately obtained according to the 3D data obtained from the environment, so that the whole process is simple and convenient, and the calculated amount is small.

Description

Technical Field

[0001] This application relates to the field of imaging, and more specifically, to methods and apparatus, computer devices and storage media for obtaining the position of a hinge. Background Technology

[0002] The 3D position of the grab bucket in a grab unloader (GSU) is used to guide operators in loading and unloading cargo from a docked cargo ship. This relies heavily on manual operation and incurs high labor costs. Automated unloading control systems can effectively reduce these costs. Determining the 3D position of the grab bucket is a critical issue for such systems. However, due to the high speed of the grab bucket and the strict requirements on the hook position, it is difficult to obtain the precise 3D position of the grab bucket in real time. Summary of the Invention

[0003] The summary of this invention is provided to introduce selected concepts in a simplified form, which will be further described in the detailed description below. This summary is not intended to identify any key or essential features of the claimed subject matter, nor is it intended to help determine the scope of the claimed subject matter.

[0004] Based on this, this application discloses a method for obtaining the position of a hinge, comprising: obtaining 3D data of the environment in which the hinge is located and converting the 3D data of the environment into 2D data; determining the 2D position of the grab in the 2D data based on the boundary frame of the grab; obtaining the 3D space of the grab based on the 2D position of the grab; determining the 3D space of the hinge based on the 3D space of the grab; and determining the 3D position of the hinge in the 3D data of the environment based on the 3D space of the hinge.

[0005] In the aforementioned manner, the position of the hinge can be accurately obtained based on 3D data obtained from the environment, making the whole process simple and convenient, and requiring little computation.

[0006] In addition, obtaining 3D data of the environment in which the hinge is located and converting the 3D data of the environment into 2D data includes: obtaining 3D data of pre-calibrated aligned coordinate axes, and obtaining multiple 2D data by projecting onto a 2D coordinate plane.

[0007] In this manner, 3D data can be converted into multiple 2D data points while aligning the coordinate axes, which facilitates subsequent analysis and use.

[0008] Furthermore, determining the 2D position of the grab in 2D data based on the grab's boundary frame includes: determining the 2D position of the grab's minimum bounding box in different 2D coordinate systems by using a neural network or object detection box.

[0009] In the aforementioned manner, the precise position coordinates can be obtained by using a neural network or another object detection box to determine the 2D position of the grab's minimum bounding box.

[0010] In addition, determining the 3D space of the hinge based on the 3D space of the grab includes: determining the 3D space of the hinge based on the preset position offset of the 3D space of the grab.

[0011] In the aforementioned manner, the 3D space of the hinge can be easily and conveniently determined using a grab bucket.

[0012] In addition, determining the 3D space of the grab based on its 2D position includes obtaining the 3D space of the grab based on the intersecting area of ​​the 2D positions of the grab.

[0013] In the aforementioned manner, 3D space is determined by intersecting the projections of two 2D planes, and this method is convenient and intuitive.

[0014] Furthermore, determining the 3D position of the hinge in the 3D data of the environment based on the 3D space of the hinge includes: determining the center position of the hinge based on the average value of the 3D data of the environment in the 3D space of the hinge.

[0015] The method described above calculates the average value of 3D data in a defined 3D space, which allows for the rapid acquisition of the relatively accurate center position of the hinge with minimal computational cost. Furthermore, the method is flexible and simple.

[0016] This application further discloses a device for obtaining the position of a hinge, comprising: an environment data module configured to obtain 3D data of the environment in which the hinge is located and convert the 3D data of the environment into 2D data; a boundary frame module configured to determine the 2D position of the grab in the 2D data based on the boundary frame of the grab; a grab module configured to obtain the 3D space of the grab based on the 2D position of the grab; a hinge module configured to determine the 3D space of the hinge based on the 3D space of the grab; and a position determination module configured to determine the 3D position of the hinge in the 3D data of the environment based on the 3D space of the hinge. Attached Figure Description

[0017] Embodiments of this disclosure are described in the accompanying drawings by way of example and not limitation, and similar reference numerals in the drawings denote the same or similar components.

[0018] Figure 1 This is a schematic diagram of a method for obtaining the position of a hinge according to an embodiment of this application.

[0019] Figure 2 This is a schematic diagram of a device for obtaining the position of a hinge according to an embodiment of this application.

[0020] Figure 3This is a schematic diagram of a computer device for obtaining the position of a hinge according to an embodiment of this application.

[0021] Figure label: S101 to S103: Steps 200: Equipment 201: Module 202: Module 203: Module 204: Module 300: Computer device 302: Processor 304: Memory Detailed Implementation

[0022] In the following description, numerous specific details are set forth for purposes of explanation. However, it will be understood that embodiments of the invention can be carried out without these specific details. In other instances, well-known circuits, structures, and techniques have not been shown in detail so as not to affect the understanding of this specification.

[0023] Throughout this specification, references to "an implementation," "implementation," "exemplary implementation," "some implementations," "various implementations," etc., indicate that the described embodiments of the invention may include specific features, structures, or characteristics. However, not every embodiment needs to include these specific features, structures, or characteristics. Furthermore, some embodiments may have some, all, or none of the features described with respect to other embodiments.

[0024] The implementation scenario of this application involves obtaining 3D spatial data after scanning the environment using a laser sensor. Contour extraction or position localization of some hinges is relatively difficult. Therefore, a grab bucket, which is relatively easy to capture, is used. The grab bucket's contour and 2D data are analyzed to obtain its 3D space in reverse. Then, the hinge space is further obtained by using the positional offset between the grab bucket and the hinge, and an averaging calculation is performed on the 3D data in the space to obtain the 3D position of the hinge. This method has low computational complexity, can obtain the position of the target object using a reference object, and is easily applicable to position determination scenarios and problems where hinges are difficult to capture. Furthermore, this type of design is suitable for scenarios with very strong constraints on port unloaders, such as when the position of the point cloud sensor is relatively fixed relative to the unloader, and there are very strong constraints on the positions of the unloader, the ground, and the grab bucket.

[0025] This application discloses a method for obtaining the position of a hinge, comprising: S101: Obtain 3D data of the environment in which the hinge is located and convert the 3D data of the environment into 2D data.

[0026] Specifically, 3D data of the environment in which the hinge is located can be obtained using radar sensors. This 3D data can be referred to as raw point cloud data. In some specific implementations, the raw point cloud data can be further converted into horizontally aligned data, with the beam direction of the unloader as the positive coordinate axis. The purpose is that sometimes the obtained object or environmental data has a certain angle relative to the horizontal plane. In subsequent calculations, data adjusted to be parallel to the horizontal plane and using the beam direction as the positive coordinate axis helps with subsequent analysis and calculations, thereby reducing computational complexity. The raw point cloud data can be converted into horizontally aligned data according to a predefined calibration matrix.

[0027] Furthermore, the aforementioned raw point cloud data can be mapped to three different 2D spaces. These three 2D spaces can be defined according to different viewpoints. For example, the front view is defined as the xz plane, the side view as the xy plane, and the top view as the yz plane. 3D data can be mapped independently into these three different viewpoint planes. In this case, the projection of 3D objects in the environment onto the 2D planes becomes planar shapes, such as points, planes, and lines. For example, the projection of a cube onto its corresponding plane is a rectangle. In this application, shapes such as rectangles, triangles, and rhombuses on the 2D planes can be used to subsequently determine the position of objects in 3D space.

[0028] S102: Determine the 2D position of the grab in the 2D data based on the grab's boundary frame.

[0029] The position of the grab in the 2D plane can be obtained by analyzing an image formed by the aforementioned objects in a 2D plane using a specially trained object detection data-driven model with neural networks or feature descriptors and scanning windows. The position can be 2D coordinates. The grab is an object located relative to the hinge and has reference significance, or its 2D shape boundary can be easily obtained in this application. The positional relationship between the grab and the hinge is known. For example, the relationship between the grab and the hinge is used in this embodiment of the application. The hinge is located above the grab. However, the shape of the hinge is not clear or easily obtained compared to the grab. The size and shape of the grab facilitate obtaining its 2D outline, and therefore the grab is used in this application. The positional relationship between the grab and the hinge is described in subsequent steps. In some embodiments, the boundary frame can be understood as the minimum bounding box.

[0030] S103: Obtain the 3D space of the grab based on its 2D position.

[0031] Furthermore, the 2D positions of corresponding planes in different viewpoints within the same 3D coordinate system allow us to obtain the intersection region of their 3D projections within the same 3D coordinate system. For example, using two 2D planes with different viewpoints as in the aforementioned example, we can obtain the intersection region of their 3D projections. Alternatively, it can be understood that the projections of different 2D planes extend to obtain the intersection region. In this way, the intersection space can be obtained. In this case, for the aforementioned three planes in different viewpoints, the intersection space formed after the planes intersect pairwise represents the position and size of the grab in the corresponding 2D space.

[0032] S104: Determine the 3D space of the hinge based on the 3D space of the grab bucket.

[0033] After determining the 3D space of the hinge, the 3D space of the hinge can be determined based on offset or a pre-established relationship (e.g., the distance or proportion between the grab and the hinge). In this embodiment of the application, the positions of the grab and the hinge are relatively fixed, and the size ratio of the grab to the hinge is also known in advance. Therefore, after obtaining the 3D space of the grab, for example, the size of the 3D space of the hinge can be obtained by using a position obtained by offsetting the height of the grab in a direction perpendicular to the ground as the center and reducing the length, width, and height to 1 / 5 of the length, width, and height of the grabbing area, respectively, to prepare for subsequently obtaining the 3D position of the hinge.

[0034] S105: Determine the 3D position of the hinge in the 3D data of the environment based on the 3D space of the hinge.

[0035] After obtaining the 3D space of the hinge, the hinge's position is determined based on the specific quantity and location of the environment's 3D data within that space. In some embodiments, since the environment data exists as a point cloud in an image or picture, when determining the hinge's 3D space within the image or picture, point cloud data in the hinge's 3D space can be collected and organized, and information such as the hinge's position and coordinates can be calculated to obtain the hinge's 3D position in space. In other words, benefiting from the point cloud data being uniformly filled in the hinge's 3D space, the position and coordinates of the point cloud data can be converted into the hinge's 3D position and 3D coordinates through sampling and calculation.

[0036] In the aforementioned manner, the position of the hinge can be accurately obtained based on 3D data obtained from the environment, making the whole process simple and convenient, and requiring little computation.

[0037] In addition, determining the 3D space of the hinge based on the 3D space of the grab includes: determining the 3D space of the hinge based on the preset position offset of the 3D space of the grab.

[0038] Specifically, as described in the foregoing embodiments, the prior positional relationship between the grab and the hinge is known or fixed, and the 3D space of the hinge is obtained based on the grab by adjusting a certain proportion and positional offset.

[0039] In the aforementioned manner, the 3D space of the hinge can be easily and conveniently determined using a grab bucket.

[0040] Furthermore, obtaining the 3D space of the grab based on its position in multiple different 2D coordinate systems includes obtaining the 3D space of the grab based on the intersecting regions of the 2D positions of the grab.

[0041] In some embodiments, since the three 2D coordinate systems transformed from the aforementioned 3D coordinate system are perpendicular to each other, the projection of the 2D contour in each pair of 2D coordinate systems extends to obtain an intersecting region, and the 3D space can be obtained by integrating the aforementioned intersecting region.

[0042] In the aforementioned manner, 3D space is determined by intersecting the projections of two 2D planes, and this method is convenient and intuitive.

[0043] Furthermore, determining the 3D position of the hinge in the 3D data of the environment based on the 3D space of the hinge includes: determining the center position of the hinge based on the centroid of the hinge in the 3D space of the environment.

[0044] In some embodiments, the 3D data of the environment is represented as a point cloud and uniformly distributed in the sampled environmental space. Therefore, the center position of the hinge can be obtained by averaging the 3D data of the environment in the 3D space of the hinge. Other similar spaces can also be calculated in this manner.

[0045] In the aforementioned manner, the average value of 3D data is calculated in a defined 3D space, which allows for the rapid acquisition of the relatively accurate center position of the hinge.

[0046] In addition, obtaining 3D data of the environment in which the hinge is located and converting the 3D data of the environment into 2D data includes: obtaining 3D data of pre-calibrated aligned coordinate axes, and obtaining multiple 2D data by projecting onto a 2D coordinate plane.

[0047] Specifically, firstly, pre-calibrated 3D data with aligned coordinate axes is obtained, and then the 3D data is converted into multiple 2D data by projecting onto a 2D coordinate plane.

[0048] In this manner, 3D data can be converted into multiple 2D data points while aligning the coordinate axes, which facilitates subsequent analysis and use.

[0049] Furthermore, determining the 2D position of the grab in the 2D data based on the grab's boundary frames includes: The minimum bounding box of the grab can be determined in 2D coordinate systems by using neural networks or object detection boxes.

[0050] Specifically, the minimum bounding box of the grab is determined to lie in different 2D coordinate systems by using a neural network trained with 2D data of the corresponding projection or another object detection model trained or configured using feature description and scanning windows. In the aforementioned manner, the 2D position of the minimum bounding box of the grab can be determined by using a neural network or another object detection box to obtain accurate position coordinates.

[0051] In related technologies, existing solutions for providing 3D positional information about the grab bucket include methods based on position sensors or images: Real-time kinematic (RTK) is a high-precision positioning sensor based on GPS. RTK is the optimal choice for positioning grabs. However, RTK requires extremely high installation and maintenance costs. Most importantly, RTK has strict limitations on its use because it relies on the Global Navigation Satellite System (GNSS) to provide positioning information.

[0052] RGB images can provide intuitive information about the operational area of ​​a global navigation satellite system. Through image processing methods, such as 3D reconstruction or calibration, RGB images can provide captured location information.

[0053] However, natural images are easily affected by the environment, and therefore prone to incorrect detection or missed detection.

[0054] To solve the aforementioned problems, such as Figure 1 As shown in the illustration, in this patent, the precise 3D position of the grab and hinge is automatically extracted using a 3D object positioning system based on a lidar sensor.

[0055] First, raw point cloud data is acquired from the lidar sensor, and then the raw point cloud data is converted into a horizontally aligned space using a predefined calibration matrix.

[0056] Next, the calibrated point cloud is mapped into different 2D spaces from three different perspectives: the front view (xz plane), the side view (xy plane), and the top view (yz plane).

[0057] Next, multiple (two in this application) specially trained data-driven models are used to detect the position of the grappling hook in each viewpoint individually. The detected position of the grappling hook is represented as an axis-aligned minimum bounding box.

[0058] Obtain the minimum bounding box from two or more viewpoints. Find the intersection region of the 3D projections of the minimum bounding boxes on each plane in the same 3D coordinate system. In the current input, the intersection region can be considered as the 3D position of the grab.

[0059] Since the hinge region of the grab is a rigid object without any shape deformation, the position of the hinge is used as the final output of the grab's position. The hinge region is selected by a preset offset on the grab's 3D bounding box.

[0060] Finally, the 3D position is estimated by averaging all point clouds over the hinge region. The 3D position is the center of the hinge.

[0061] A lidar sensor is used as the raw input in the method. LiDAR sensors can handle large environmental variations and are virtually unaffected by different textures of objects. Due to the robustness and small error of point clouds, lidar sensors can achieve the same accuracy as more expensive sensors.

[0062] In terms of algorithmic pipeline, the method avoids object detection based on 3D convolution, thus significantly reducing computational costs. Therefore, the method can be integrated into lightweight devices and run in real time. Furthermore, multiple models are used based on different viewpoints. Therefore, even if detection fails in one viewpoint, the approximate position of the grab can still be determined.

[0063] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but the steps are not necessarily performed in the order indicated by the arrows. Unless expressly stated herein, there is no strict order constraint on the execution of these steps, and they may be performed in other orders. Furthermore, Figure 1 At least some of the steps may include multiple steps or stages that are not necessarily executed and completed at the same time but may be executed at different times, and the order in which these steps or stages are executed is not necessarily sequential, but may be executed sequentially or alternately with other steps or at least some of the steps or stages.

[0064] Figure 2 A device 200 for obtaining the position of a hinge is provided, comprising: The environmental data module 201 is configured to obtain 3D data of the environment in which the hinge is located and convert the 3D data of the environment into 2D data. Boundary frame module 202 is configured to determine the 2D position of the grab in 2D data based on the boundary frame of the grab; Grab module 203, configured to obtain the 3D space of the grab based on the 2D position of the grab; Hinge module 204, configured to determine the 3D space of the hinge based on the 3D space of the grab bucket; and The position determination module 205 is configured to determine the 3D position of the hinge in the 3D data of the environment based on the 3D space of the hinge.

[0065] In addition, the environmental data module 201 is configured to obtain pre-calibrated 3D data with aligned coordinate axes, and to obtain multiple 2D data by projecting onto a 2D coordinate plane.

[0066] In addition, the boundary frame module 202 is configured to determine the 2D position of the minimum bounding box of the grab in different 2D coordinate systems by using a neural network or object detection box.

[0067] In addition, the hinge module 204 is configured to determine the 3D space of the hinge based on a preset position of the 3D spatial offset of the grab bucket.

[0068] In addition, the grab module 203 is configured to obtain the 3D space of the grab based on the intersection area of ​​the 2D positions of the grab.

[0069] In addition, the position determination module 205 is configured to determine the center position of the hinge based on the average value of the 3D data of the environment in the 3D space of the hinge.

[0070] It should be noted that the device may contain more or fewer modules to implement the described functions. For example, Figure 2 At least one module in the device 200 may be further divided into multiple different sub-modules. Each sub-module is configured to perform at least some of the operations described herein in conjunction with a corresponding module. Additionally, in some instances, the device 200 may further include an additional module configured to perform another operation described herein. Furthermore, those skilled in the art will understand that the exemplary device 200 can be implemented using software, hardware, firmware, or any combination thereof.

[0071] Figure 3 A computer device is provided. According to an embodiment, the computer device 300 may include a processor 302. The processor 302 executes a computer program stored in a memory 304. The computer program, when executed by the processor, implements the aforementioned methods.

[0072] Those skilled in the field can understand. Figure 3 The structures shown are merely block diagrams of a portion of the structure related to the solution in this application, and the diagrams do not constitute a limitation on the computer apparatus to which this application is applied. A particular computer apparatus may contain more or fewer components than those shown in the diagrams, or may combine some components, or may deploy using different components.

[0073] Those skilled in the art will understand that all or some of the processes of the methods in the foregoing embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, the processes of the foregoing method embodiments can be implemented. References to memory, storage devices, databases, or other media used in the embodiments provided in this application can all include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, etc. Volatile memory can include random access memory (RAM) or external cache. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0074] This application further provides a computer-readable storage medium for storing a computer program, wherein the computer program performs the aforementioned steps when executed by a processor.

[0075] This application further provides a computer program product, wherein the computer program product is tangibly stored in a computer-readable medium and includes computer-executable instructions, which perform the aforementioned steps when executed by at least one processor.

[0076] Furthermore, the computer program can be stored in and run on the cloud to execute the method. Additionally, components of the program can be deployed on multiple devices or in the cloud. For example, corresponding steps can be deployed and run on a home or local computer, or run on different cloud devices transmitting signals via a communication connection, or deployed and run on a home or local computer. This application does not limit the described manner or method, and the corresponding technologies can be flexibly deployed and arranged to fully utilize cloud, big data, supercomputing power, and other devices and technologies for executing and completing the method.

[0077] Some embodiments of this disclosure may include artifacts. Artifacts may comprise storage media configured to store logic. Examples of storage media may include one or more types of computer-readable storage media capable of storing electronic data, including volatile or non-volatile memory, removable or non-removable memory, erasable or non-erasable memory, writable or rewritable memory, etc. Examples of logic may include various software units, such as software components, programs, applications, computer programs, application programs, system programs, machine programs, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, procedures, software interfaces, application programming interfaces (APIs), instruction sets, operational code, computer code, code segments, computer code segments, words, values, symbols, or any combination thereof. In some embodiments, for example, the article of manufacture may store executable computer program instructions that, when executed by a processor, cause the processor to perform the methods and / or operations described herein. Executable computer program instructions may comprise any suitable type of code, such as source code, compiled code, interpreted code, executable code, static code, dynamic code, etc. Executable computer program instructions can be implemented according to predefined computer languages, methods, or syntaxes to command a computer to perform specific functions. Instructions can be implemented using any suitable high-level, low-level, object-oriented, visual, compiled, and / or interpreted programming language.

[0078] The foregoing description contains examples of the disclosed architecture. It is certainly impossible to describe every conceivable combination of components and / or methods, but those skilled in the art will appreciate that many other combinations and arrangements are possible. Therefore, the novel architecture is intended to cover all such alternatives, modifications, and variations that fall within the spirit and scope of the appended claims.

Claims

1. A method for obtaining the position of a hinge, comprising: Obtain 3D data of the environment in which the hinge is located and convert the 3D data of the environment into 2D data; The 2D position of the grab in the 2D data is determined based on the boundary frame of the grab; The 3D space of the grab is obtained based on the 2D position of the grab; The 3D space of the hinge is determined based on the 3D space of the grab; and The 3D position of the hinge in the 3D data of the environment is determined based on the 3D space of the hinge.

2. The method of claim 1, wherein obtaining 3D data of the environment in which the hinge is located, and converting the 3D data of the environment into 2D data, comprises: Obtain pre-calibrated aligned coordinate axis 3D data, and obtain multiple 2D data by 2D coordinate plane projection.

3. The method of claim 1, wherein determining the 2D position of the grab in the 2D data based on the grab's boundary frame comprises: The minimum bounding box of the grab is determined in 2D in different 2D coordinate systems by using a neural network or object detection box.

4. The method of claim 1, wherein determining the 3D space of the hinge based on the 3D space of the grab comprises: The 3D space of the hinge is determined based on the preset position of the 3D spatial offset of the grab.

5. The method according to claim 1, wherein obtaining the 3D space of the grab based on the 2D position of the grab comprises: The 3D space of the grab is obtained by the intersection area obtained from the 3D projection of the grab in different 2D coordinate systems.

6. The method of claim 1, wherein determining the 3D position of the hinge in the 3D data of the environment based on the 3D space of the hinge comprises: The center position of the hinge is determined based on the 3D data of the environment and the centroid of the hinge in the 3D space.

7. A device (200) for obtaining the position of a hinge, comprising: An environment data module (201) is configured to obtain 3D data of the environment in which the hinge is located, and to convert the 3D data of the environment into 2D data. Boundary frame module (202) is configured to determine the 2D position of the grab in the 2D data based on the boundary frame of the grab; A grab module (203) configured to obtain the 3D space of the grab based on the 2D position of the grab; A hinge module (204) configured to determine the 3D space of the hinge based on the 3D space of the grab; and A position determination module (205) is configured to determine the 3D position of the hinge in the 3D data of the environment based on the 3D space of the hinge.

8. The device (200) according to claim 7, wherein The environmental data module (201) is configured to obtain pre-calibrated 3D data with aligned coordinate axes and to obtain multiple 2D data by projecting 2D coordinate planes.

9. The device (200) according to claim 7, wherein The boundary frame module (202) is configured to determine the 2D position of the minimum bounding box of the grab in different 2D coordinate systems by using a neural network or object detection box.

10. The device (200) according to claim 7, wherein The hinge module (204) is configured to determine the 3D space of the hinge based on a preset position of the 3D spatial offset of the grab.

11. The device (200) according to claim 7, wherein The grab module (203) is configured to obtain the 3D space of the grab based on the intersecting regions obtained from the 3D projections of the grab in different 2D coordinate systems.

12. The device (200) according to claim 7, wherein The position determination module (205) is configured to determine the center position of the hinge in the 3D coordinate system based on the centroid of the hinge in the 3D space of the 3D point cloud of the environment.

13. A computer apparatus comprising a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program, performs the steps of the method according to any one of claims 1 to 6.

14. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, performs the steps of the method according to any one of claims 1 to 6.

15. A computer program product, wherein the computer program product is tangibly stored in a computer-readable medium and includes computer-executable instructions, wherein the computer-executable instructions, when executed by at least one processor, perform the steps of the method according to any one of claims 1 to 6.

Images