Antenna engineering parameter determination method, apparatus and system, and storage medium

Abstract

The present application relates to the technical field of communications. Disclosed are an antenna engineering parameter determination method, apparatus and system, and a storage medium, which are used for solving the problems in the related art of high cost and low efficiency in determining antenna engineering parameters and the determined antenna engineering parameters being inaccurate. The method comprises: at least on the basis of internal parameters of a first image collection apparatus, first point cloud data and a first image set, determining a sparse depth map corresponding to each image in the first image set, and a pose of the first image collection apparatus of when each image is captured; and then, on the basis of the sparse depth map corresponding to each image in the first image set, and the pose of the first image collection apparatus of when each image is captured, determining antenna engineering parameters of a target base station.

Description

Antenna engineering parameter determination method, device, system and storage medium

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on February 23, 2024, with application number 202410205808.7 and application name “Antenna Engineering Parameter Determination Method, Device, System and Storage Medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and in particular to a method, device, system and storage medium for determining antenna working parameters. Background Art

[0003] In mobile communication networks, antenna parameters are crucial for network optimization. These parameters are susceptible to changes due to factors such as weather, and may require irregular adjustments for network optimization. Therefore, they require regular measurement and verification.

[0004] Currently, drones are often used as carriers, equipped with image acquisition devices, to capture images from multiple perspectives around base stations. These images are then used to perform a 3D reconstruction of the base station, and the antenna parameters for each antenna on the base station are determined based on the 3D reconstruction.

[0005] The above-mentioned method of using drones to take photos and determine antenna working parameters not only has problems such as high cost and low efficiency, but also when performing three-dimensional reconstruction of the base station based on photos from multiple perspectives, the photo perspective is limited, resulting in an incomplete three-dimensional reconstructed base station, which in turn makes the determined antenna working parameters inaccurate. Summary of the Invention

[0006] The embodiments of the present application provide a method, device, system and storage medium for determining antenna working parameters, which can improve the accuracy of the determined antenna working parameters when determining the antenna working parameters, while reducing measurement costs and improving work efficiency.

[0007] To achieve the above objectives, the present invention provides the following technical solutions:

[0008] In a first aspect, a method for determining antenna operating parameters is provided. This method can be executed by a server in an antenna operating parameter determination system; alternatively, it can be executed by a module implemented in the server, such as a chip, chip system, or circuit; or alternatively, it can be implemented by a logic module or software that implements all or part of the server's functions, without limitation. For ease of description, the following description uses server execution as an example.

[0009] The method includes determining a sparse depth map corresponding to each image in the first image set and the pose of the first image acquisition device when each image was captured based on at least intrinsic parameters of a first image acquisition device, first point cloud data, and a first image set. Subsequently, antenna engineering parameters of a target base station are determined based on the sparse depth map corresponding to each image in the first image set and the pose of the first image acquisition device when each image was captured.

[0010] Each image in the first image set is taken by the first image acquisition device and includes an image of the antenna of the target base station.

[0011] The resolution of each image in the first image set is greater than a resolution threshold. The resolution threshold may be preset.

[0012] The sparse depth map corresponding to each image is used to indicate the distance between the first image acquisition device and the antenna in the image.

[0013] The first point cloud data is obtained by the laser radar and is point cloud data in the laser radar coordinate system.

[0014] In the above technical solution, when determining the antenna engineering parameters of the target base station, it is only necessary to use a first image acquisition device, a laser radar and a server to realize the survey of the antenna engineering parameters of the target base station without the need to use a drone for shooting. Therefore, it can effectively solve the problems of high cost and low efficiency caused by drones in related technologies.

[0015] In addition, when determining the antenna working parameters, the present application determines them based on the sparse depth map corresponding to each image in the first image set and the position of the first image acquisition device when each image is taken. The sparse depth map corresponding to each image and the position of the first image acquisition device when each image is taken can be determined based on the internal parameters of the first image acquisition device, the first point cloud data acquired by the laser radar, and the first image set acquired by the first image acquisition device. It is not necessary to determine the antenna working parameters of each antenna on the base station based on the three-dimensionally reconstructed base station, so there is no need to use photos from multiple perspectives to perform three-dimensional reconstruction of the base station, thereby effectively avoiding the problem of inaccurate antenna working parameters caused by limited photo viewing angles in related technologies.

[0016] In an optional embodiment, when determining the antenna parameters of the target base station based on the sparse depth map corresponding to each image in the first image set and the posture of the first image acquisition device when taking each image, for each image in the first image set, the server can determine the three-dimensional coordinates of at least one pixel point contained in the target area of ​​the image in the world coordinate system based on the sparse depth map of the image and the posture of the first image acquisition device when taking the image, and determine at least one second image set containing the same antenna from the first image set based on the three-dimensional coordinates of at least one pixel point contained in the target area of ​​each image in the world coordinate system.

[0017] Afterwards, for each second image set, at least two images are determined from the second image set, and for the same corner point in the at least two images, based on the two-dimensional coordinates of the corner point in the image coordinate system and the posture of the first image acquisition device when taking each of the at least two images, the three-dimensional coordinates of the corner point in the world coordinate system are determined to obtain the three-dimensional coordinates of each corner point of the antenna in the second image set in the world coordinate system.

[0018] Finally, the server may determine the antenna working parameters of each antenna based on the three-dimensional coordinates of each corner point of each antenna in the world coordinate system to obtain the antenna working parameters of the target base station.

[0019] The target area of ​​each image is determined based on the corner points of the antenna in the image.

[0020] In the above technical solution, each image can be classified by firstly using the sparse depth map of each image in the first image set and the posture of the first image acquisition device when the image is taken, and then a second image set containing the same antenna can be determined. Then, the two-dimensional coordinates of each corner point of the antenna in the second image set in the image coordinate system are converted into three-dimensional coordinates of each corner point in the world coordinate system. Finally, the antenna working parameters of the target base station are determined according to the three-dimensional coordinates of each corner point of each antenna in the world coordinate system. It can be seen from this that when determining the antenna working parameters of the target base station, the key of this application is to realize the transformation of each corner point of the antenna from two-dimensional coordinates (i.e., image coordinate system) to three-dimensional coordinates (i.e., world coordinate system) without the need to perform three-dimensional reconstruction of the target base station, i.e., there is no need to obtain photos from multiple perspectives and use photos from multiple perspectives to perform three-dimensional reconstruction of the base station. Therefore, the problem of inaccurate antenna working parameters caused by limited photo viewing angles in the related technology can be effectively avoided.

[0021] In an optional implementation, the at least two images include a first image and a second image.

[0022] On this basis, when determining the three-dimensional coordinates of the corner point in the world coordinate system based on the two-dimensional coordinates of the corner point in the image coordinate system and the posture of the first image acquisition device when shooting each of the at least two images, the relative posture between the first image and the second image can be determined based on the posture of the first image acquisition device when shooting the first image and the posture of the first image acquisition device when shooting the second image, and then the three-dimensional coordinates of the corner point in the world coordinate system can be determined based on the two-dimensional coordinates of the corner point in the image coordinate system of the first image, the two-dimensional coordinates of the corner point in the image coordinate system of the second image, and the relative posture between the first image and the second image.

[0023] In the above technical solution, a specific implementation method for determining the three-dimensional coordinates of each corner point of the antenna in the world coordinate system is provided. In this method, the two-dimensional coordinates of the corner points in the image coordinate system and the posture of the first image acquisition device when taking each image can be used to determine the three-dimensional coordinates of each corner point of the antenna in the world coordinate system, without the need to obtain photos from multiple perspectives and use photos from multiple perspectives to perform three-dimensional reconstruction of the base station to obtain the three-dimensional coordinates of each corner point of the antenna in the world coordinate system. Therefore, it can effectively avoid the problem of inaccurate antenna engineering parameters caused by limited photo viewing angles in related technologies.

[0024] In an optional embodiment, when determining at least one second image set containing the same antenna from the first image set based on the three-dimensional coordinates of at least one pixel point contained in the target area of ​​each image in the world coordinate system, the three-dimensional coordinates of the center point of the target area of ​​the image can be determined based on the three-dimensional coordinates of at least one pixel point contained in the target area of ​​each image in the world coordinate system, and then based on the three-dimensional coordinates of the center point of the target area of ​​each image, at least one second image set containing the same antenna can be determined from the first image set.

[0025] In the above technical solution, an implementation method for determining at least one second image set containing the same antenna from a first image set is provided, which improves the feasibility of the present application.

[0026] In an optional implementation, the first image set may include a third image and a fourth image.

[0027] On this basis, when determining multiple second image sets containing the same antenna from the first image set based on the three-dimensional coordinates of the center point of the target area of ​​each image, the relative distance between the center point of the target area of ​​the third image and the center point of the target area of ​​the fourth image can be determined based on the three-dimensional coordinates of the center point of the target area of ​​the third image and the three-dimensional coordinates of the center point of the target area of ​​the fourth image. Then, when the relative distance is less than the distance threshold, it is determined that the third image and the fourth image contain the same antenna, and finally it is determined that the third image and the fourth image belong to the same second image set.

[0028] The distance threshold may be pre-set, and this application does not limit the distance threshold. For example, the distance threshold may be 50 centimeters or 45 centimeters.

[0029] In the above technical solution, a specific implementation method of determining whether the third image and the fourth image belong to the same second image set is described, which can further improve the feasibility of the present application.

[0030] In an optional embodiment, when determining the antenna working parameters of the antenna based on the three-dimensional coordinates of each corner point of each antenna, for each antenna, the server can classify the corner points in the antenna based on the three-dimensional coordinates of the corner points in the antenna to obtain N types of corner points, and then use the center point of each type of corner point as the target corner point of the antenna. After obtaining N target corner points, the server can determine the antenna working parameters of the antenna based on the three-dimensional coordinates of the N target corner points.

[0031] Wherein, N is a positive integer. For example, N is 4.

[0032] In the above technical solution, a specific implementation method is provided for determining the antenna engineering parameters of each antenna based on the three-dimensional coordinates of each corner point of each antenna. Through this method, there is no need to reconstruct the base station through photos from multiple perspectives. Therefore, it can effectively avoid the problem of inaccurate antenna engineering parameters caused by limited photo viewing angles in related technologies.

[0033] In an optional implementation, the first image set may include a fifth image.

[0034] On this basis, the above-mentioned method can determine the sparse depth map corresponding to each image in the first image set, and the posture of the first image acquisition device when taking each image, based at least on the internal parameters of the first image acquisition device, the first point cloud data and the first image set. It can first obtain the time-series posture sequence of the lidar based on the first point cloud data, and then determine the posture of the first image acquisition device when taking the fifth image based on the time-series posture sequence of the lidar and the fifth image. Finally, based on the posture of the first image acquisition device when taking the fifth image and the internal parameters of the first image acquisition device, determine the sparse depth map corresponding to the fifth image.

[0035] Among them, the time-series pose sequence of the lidar includes the pose of the lidar at each moment.

[0036] The position and posture of the laser radar at each moment can be understood as the position and posture of the laser radar at each moment.

[0037] In the above technical solution, taking the fifth image as an example, a method is provided for determining a sparse depth map corresponding to the fifth image and the position of the first image acquisition device when the fifth image is captured. Specifically, when capturing the fifth image, the position of the first image acquisition device can be determined by the position of the laser radar at various times and the fifth image. The sparse depth map corresponding to the fifth image can be determined by the position of the first image acquisition device and the internal parameters of the first image acquisition device when the fifth image is captured. This further improves the feasibility of the present application.

[0038] In an optional embodiment, when determining the posture of the first image acquisition device when taking the fifth image based on the time-series posture sequence of the lidar and the fifth image, the first target posture at the two moments closest to the timestamp of the fifth image can be first determined from the time-series posture sequence of the lidar, and then the posture of the first image acquisition device when taking the fifth image can be determined based on the first target posture and the relative external parameters of the first image acquisition device and the lidar.

[0039] The timestamp of the fifth image is used to indicate the time when the fifth image is captured.

[0040] In the above technical solution, a specific implementation method for determining the posture of the first image acquisition device when shooting the fifth image is provided. On the basis of improving the feasibility of this application, it can effectively improve the accuracy of determining the posture of the first image acquisition device when shooting the fifth image, so that the accuracy of determining the antenna working parameters of the target base station can be effectively improved based on the posture of the first image acquisition device when shooting the fifth image.

[0041] In an optional embodiment, when determining the sparse depth map corresponding to the fifth image based on the posture of the first image acquisition device when shooting the fifth image and the internal parameters of the first image acquisition device, the first point cloud data can be first converted into second point cloud data in the world coordinate system based on the time-series posture sequence of the lidar, and then the second point cloud data can be processed based on the posture of the first image acquisition device when shooting the fifth image to obtain the point cloud data corresponding to the fifth image. Finally, based on the posture of the first image acquisition device when shooting the fifth image and the point cloud data corresponding to the fifth image, the sparse depth map corresponding to the fifth image is determined.

[0042] In the above technical solution, a specific implementation method for determining the sparse depth map corresponding to the fifth image is provided, which can effectively improve the accuracy of determining the sparse depth map corresponding to the fifth image on the basis of improving the feasibility of this application, so that the accuracy of determining the antenna working parameters of the target base station can be effectively improved based on the sparse depth map corresponding to the fifth image.

[0043] In an optional embodiment, the first image acquisition device is a telephoto camera.

[0044] In an optional implementation, the antenna engineering parameter determination system may further include a second image acquisition device.

[0045] On this basis, the above-mentioned method can determine the sparse depth map corresponding to each image in the first image set, as well as the posture of the first image acquisition device when taking each image, based at least on the internal parameters of the first image acquisition device, the first point cloud data and the first image set. It can also determine the sparse depth map corresponding to each image in the first image set, as well as the posture of the first image acquisition device when taking each image, based on the internal parameters of the first image acquisition device, the internal parameters of the second image acquisition device, the first point cloud data, the first image set and the panoramic image set.

[0046] Each panoramic image in the panoramic image set is taken by the second image acquisition device and contains an image of the target base station and the scene where the target base station is located.

[0047] In the above technical solution, when determining the antenna engineering parameters of the target base station, the second image acquisition device, the first image acquisition device, the laser radar and the server are used to realize the survey of the antenna engineering parameters of the target base station without the need to use a drone for shooting. Therefore, it can also effectively avoid the problems of high cost and low efficiency caused by drones in related technologies.

[0048] In addition, the above technical solution determines the antenna engineering parameters based on the sparse depth map corresponding to each image in the first image set and the position of the first image acquisition device when each image was captured. The sparse depth map corresponding to each image and the position of the first image acquisition device when each image was captured can be determined based on the internal parameters of the first image acquisition device, the internal parameters of the second image acquisition device, the first point cloud data acquired by the lidar, the first image set acquired by the first image acquisition device, and the panoramic image set acquired by the second image acquisition device. It is not necessary to determine the antenna engineering parameters of each antenna on the base station based on the three-dimensionally reconstructed base station, and therefore it is not necessary to use photos from multiple perspectives to perform three-dimensional reconstruction of the base station, thereby effectively avoiding the problem of inaccurate antenna engineering parameters caused by the limited perspective of the photos in the related art.

[0049] In an optional embodiment, when determining the sparse depth map corresponding to each image in the first image set based on the internal parameters of the first image acquisition device, the internal parameters of the second image acquisition device, the first point cloud data, the first image set and the panoramic image set, as well as the posture of the first image acquisition device when shooting each image, the posture of the second image acquisition device when shooting each panoramic image can be first determined based on the first point cloud data and the panoramic image set, and then the sparse depth map corresponding to each panoramic image can be determined based on the posture of the second image acquisition device when shooting each panoramic image and the internal parameters of the second image acquisition device.

[0050] Finally, based on the intrinsic parameters of the first image acquisition device, the first image set, the posture of the second image acquisition device when taking each panoramic image, the sparse depth map corresponding to each panoramic image, and the relative extrinsic parameters of the first image acquisition device and the second image acquisition device, the sparse depth map corresponding to each image in the first image set and the posture of the first image acquisition device when taking each image are determined.

[0051] In the above technical solution, another method for determining the sparse depth map corresponding to each image in the first image set and the position of the first image acquisition device when each image is captured is provided. Specifically, the position of the second image acquisition device when capturing each panoramic image and the sparse depth map corresponding to each panoramic image can be first determined. Then, based on the position of the second image acquisition device when capturing each panoramic image and the sparse depth map corresponding to each panoramic image, the sparse depth map corresponding to each image in the first image set and the position of the first image acquisition device when capturing each image are derived. This expands the scope of protection of the present application and further enhances the feasibility of the solution of the present application.

[0052] In an optional embodiment, when determining the position and posture of the second image acquisition device when taking each panoramic image based on the first point cloud data and the panoramic image set, the time-series position and posture sequence of the lidar can be first obtained based on the first point cloud data, and then the position and posture of the second image acquisition device when taking each panoramic image can be determined based on the time-series position and posture sequence of the lidar and the panoramic image set.

[0053] The time series pose sequence of the lidar contains the pose of the lidar at each moment.

[0054] In the above technical solution, a specific implementation method for determining the posture of the second image acquisition device when shooting each panoramic image is provided. On the basis of improving the feasibility of this application, the posture of the second image acquisition device when shooting each panoramic image can be accurately determined, so that the posture of the first image acquisition device when shooting each image can be accurately determined based on the posture of the second image acquisition device when shooting each panoramic image, and then the antenna working parameters of the target base station can be accurately determined.

[0055] In an optional implementation, the first image set includes a sixth image.

[0056] On this basis, when determining the sparse depth map corresponding to each image in the first image set and the posture of the first image acquisition device when shooting each image based on the intrinsic parameters of the first image acquisition device, the first image set, the posture of the second image acquisition device when shooting each panoramic image, the sparse depth map corresponding to each panoramic image, and the relative extrinsic parameters of the first image acquisition device and the second image acquisition device, the second target posture at the two moments closest to the timestamp of the sixth image can be first determined from the posture of the second image acquisition device when shooting each panoramic image.

[0057] Afterwards, the posture of the first image acquisition device when taking the sixth image can be determined based on the posture of the second target and the relative external parameters of the first image acquisition device and the second image acquisition device. Then, based on the posture of the first image acquisition device when taking the sixth image and the sparse depth map corresponding to the target panoramic image, the sparse depth map corresponding to the sixth image can be determined.

[0058] The target panoramic image includes at least one panoramic image corresponding to the second target posture.

[0059] The timestamp of the sixth image is used to indicate the time when the sixth image is captured.

[0060] In the above technical solution, taking the sixth image as an example, a method is provided for determining a sparse depth map corresponding to the sixth image and the posture of the first image acquisition device when shooting the sixth image, which can further improve the feasibility of the present application.

[0061] In an optional embodiment, the second image acquisition device is a panoramic camera.

[0062] In the second aspect, an antenna working parameter determination device is provided, which is located on a server in an antenna working parameter determination system and includes: a functional unit for executing any one of the methods provided in the first aspect, wherein the actions performed by each functional unit are implemented through hardware or through hardware executing corresponding software implementations.

[0063] The device includes a first determining module and a second determining module; wherein,

[0064] The first determination module is configured to determine a sparse depth map corresponding to each image in the first image set, and a position of the first image acquisition device when each image was captured, based at least on the internal parameters of the first image acquisition device, the first point cloud data, and the first image set. Each image in the first image set is captured by the first image acquisition device and includes an image of an antenna of a target base station. The resolution of each image in the first image set is greater than a resolution threshold. The sparse depth map corresponding to each image is used to indicate the distance between the first image acquisition device and the antenna in the image. The first point cloud data is point cloud data in the coordinate system of a laser radar.

[0065] The second determination module is used to determine the antenna working parameters of the target base station based on the sparse depth map corresponding to each image in the first image set and the posture of the first image acquisition device when taking each image.

[0066] In a third aspect, a computing device cluster is provided, comprising at least one computing device, each computing device comprising a processor and a memory; the processor of the at least one computing device is used to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster executes the antenna engineering parameter determination method provided in the aforementioned first aspect or any optional embodiment of the first aspect.

[0067] In a fourth aspect, a system for determining antenna working parameters is provided, which includes: a first image acquisition device, a laser radar, and a server; the first image acquisition device is used to acquire a first image set, the laser radar is used to acquire first point cloud data, and the server is used to execute the antenna working parameter determination method provided by the first aspect or any optional embodiment of the first aspect.

[0068] In a fifth aspect, a computer-readable storage medium is provided, comprising computer execution instructions. When the computer execution instructions are run on a computer, the computer executes the antenna engineering parameter determination method provided in the aforementioned first aspect or any optional embodiment of the first aspect.

[0069] In the sixth aspect, a chip is provided, which includes: a processor and an interface circuit; the interface circuit is used to receive code instructions and transmit them to the processor; the processor is used to run the code instructions to execute the antenna working parameter determination method provided by the first aspect or any optional embodiment of the first aspect.

[0070] In the seventh aspect, a computer program product is provided, comprising computer execution instructions. When the computer execution instructions are run on a computer, the computer executes the antenna engineering parameter determination method provided in the aforementioned first aspect or any optional embodiment of the first aspect.

[0071] It should be noted that the technical effects brought about by any implementation method in the second to seventh aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] FIG1 is a schematic diagram of a signal transmission provided in the related art;

[0073] FIG2 is an application scenario diagram of an antenna engineering parameter determination system provided in an embodiment of the present application;

[0074] FIG3 is a schematic structural diagram of a data acquisition device provided in an embodiment of the present application;

[0075] FIG4 is a line diagram between a first image acquisition device and a base station provided by an embodiment of the present application;

[0076] FIG5 is an application scenario diagram of another antenna engineering parameter determination system provided in an embodiment of the present application;

[0077] FIG6 is a schematic diagram of the structure of another data acquisition device provided in an embodiment of the present application;

[0078] FIG7 is a schematic diagram of an interactive flow of a method for determining antenna working parameters provided in an embodiment of the present application;

[0079] FIG8 is a schematic diagram of a process for determining a sparse depth map corresponding to a fifth image and a position of a first image acquisition device when capturing the fifth image, provided by an embodiment of the present application;

[0080] FIG9 is a schematic diagram of a process for determining antenna parameters of a target base station according to an embodiment of the present application;

[0081] FIG10 is a schematic diagram of an epipolar constraint provided in an embodiment of the present application;

[0082] FIG11 is a schematic diagram of an interactive process of another method for determining antenna engineering parameters provided in an embodiment of the present application;

[0083] FIG12 is a schematic diagram of an interactive process of another method for determining antenna working parameters provided in an embodiment of the present application;

[0084] FIG13 is a schematic diagram of a process for determining a sparse depth map corresponding to each image in a first image set and a position of a first image acquisition device when capturing each image, provided by an embodiment of the present application;

[0085] FIG14 is a structural block diagram of an antenna engineering parameter determination system provided in an embodiment of the present application;

[0086] FIG15 is a structural block diagram of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0087] In the description of this application, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "a plurality" means two or more. Words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not limit them to be necessarily different.

[0088] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0089] "Used to indicate" can include direct indication and indirect indication, and can also include explicit indication and implicit indication. When describing "a certain indication information is used to indicate A" or "indication information of A", it can include that the indication information directly indicates A or indirectly indicates A, but it does not mean that the indication information must carry A. The information indicated by a certain information (such as the configuration information described below) is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, directly indicating the information to be indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, where there is an association between the other information and the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, the indication of specific information can be achieved by using the arrangement order of each information agreed in advance (such as specified by the protocol), thereby reducing the indication overhead to a certain extent. At the same time, the common parts of each information can be identified and indicated in a unified manner to reduce the indication overhead caused by indicating the same information separately. For example, those skilled in the art will appreciate that a precoding matrix is ​​composed of precoding vectors, and the precoding vectors in the precoding matrix may share common components in terms of composition or other attributes. Furthermore, the specific indication method may also be various existing indication methods, such as, but not limited to, the aforementioned indication methods and their various combinations. The specific details of various indication methods can be referenced in the prior art and will not be elaborated herein. As can be seen from the foregoing, for example, when multiple pieces of information of the same type need to be indicated, different indication methods may be used for different pieces of information. During implementation, the desired indication method can be selected based on specific needs. The embodiments of this application do not limit the selected indication method. Thus, the indication methods described in the embodiments of this application should be understood to encompass various methods for enabling the intended party to obtain information about the information to be indicated. The information to be indicated may be sent as a whole or as multiple sub-information, and the transmission periods and / or transmission timings of these sub-information may be the same or different. The specific transmission method is not limited herein. The transmission periods and / or transmission timings of these sub-information may be predefined, for example, according to a protocol, or may be configured by the transmitting device by sending configuration information to the receiving device. The configuration information may include, for example but not limited to, one of radio resource control signaling, medium access control (MAC) layer signaling, and physical layer signaling, or a combination of at least two of them.The radio resource control signaling includes, for example, radio resource control (RRC) signaling; the MAC layer signaling includes, for example, a MAC control element (CE); and the physical layer signaling includes, for example, downlink control information (DCI).

[0090] During signal transmission, signals are often affected by the physical environment and antenna parameters. Therefore, accurate measurement of the physical environment and antenna parameters is crucial for network optimization.

[0091] The physical environment refers to the three-dimensional spatial information within an area, including the location and occupancy of objects such as buildings, trees, and signage that affect signal propagation, as shown in Figure 1. Antenna engineering parameters refer to key parameters that influence antenna signal propagation, such as the height, latitude and longitude, azimuth, and downtilt of network elements such as base station antennas. These parameters directly affect signal propagation.

[0092] When measuring the physical environment, measurements can be performed using equipment and methods that obtain high-precision maps, such as map collection vehicles.

[0093] When measuring antenna parameters, non-contact methods are generally used for individual measurements because base station antennas and other network elements have the characteristics of high height, long distance and small size.

[0094] Currently, drones are often used as carriers, equipped with image acquisition devices, to capture images of base stations from multiple perspectives. These images are then used to perform a 3D reconstruction of the base station, and the antenna parameters of each antenna on the base station are determined based on the 3D reconstruction.

[0095] However, the above-mentioned method of using drones to take photos and determine antenna working parameters not only has problems such as high cost and low efficiency, but also when performing three-dimensional reconstruction of the base station based on photos from multiple perspectives, the photo perspective is limited, resulting in an incomplete three-dimensional reconstructed base station, which in turn makes the determined antenna working parameters inaccurate.

[0096] In view of this, an embodiment of the present application provides a method for determining antenna engineering parameters. A server in an antenna engineering parameter determination system can determine a sparse depth map corresponding to each image in the first image set, as well as the position of the first image acquisition device when each image was captured, based at least on the intrinsic parameters of the first image acquisition device, first point cloud data, and the first image set. Subsequently, the antenna engineering parameters of the target base station are determined based on the sparse depth map corresponding to each image in the first image set and the position of the first image acquisition device when each image was captured.

[0097] Thus, in the present application, when determining the antenna parameters of the target base station, it is only necessary to use a first image acquisition device, a laser radar and a server to realize the survey of the antenna parameters of the target base station without the need to use a drone for shooting. Therefore, it can effectively solve the problems of high cost and low efficiency caused by drones in related technologies.

[0098] In addition, when determining the antenna working parameters, the present application determines them based on the sparse depth map corresponding to each image in the first image set and the position of the first image acquisition device when each image is taken. The sparse depth map corresponding to each image and the position of the first image acquisition device when each image is taken can be determined based on the internal parameters of the first image acquisition device, the first point cloud data acquired by the laser radar, and the first image set acquired by the first image acquisition device. It is not necessary to determine the antenna working parameters of each antenna on the base station based on the three-dimensionally reconstructed base station, so there is no need to use photos from multiple perspectives to perform three-dimensional reconstruction of the base station, thereby effectively avoiding the problem of inaccurate antenna working parameters caused by limited photo viewing angles in related technologies.

[0099] Figure 2 illustrates an application scenario of an antenna engineering parameter determination system provided in an embodiment of the present application. As shown in Figure 2 , the antenna engineering parameter determination system comprises a drive test acquisition system 201 and a server 202. The drive test acquisition system 201 may include a first image acquisition device 203 and a laser radar (light detection and ranging, LIDAR) 204.

[0100] The drive test collection system 201 can respond to a user's request for data collection of the area to be tested, drive in the area to be tested at a preset speed, and collect corresponding data through the first image acquisition device 203 and the laser radar 204.

[0101] Specifically, the first image acquisition device 203 may perform long-distance photography of the antenna of the target base station at different photography moments to obtain a first image set including multiple images and send the first image set to the server 202 .

[0102] The resolution of each image in the first image set is greater than a resolution threshold to ensure that the captured image is a high-definition image. The resolution threshold may be pre-set.

[0103] In the embodiment of the present application, the first image acquisition device 203 may be a camera suitable for long-distance photography, for example, a telephoto camera with a telephoto lens.

[0104] The shooting moment of the first image acquisition device 203 may be pre-set, determined based on the position of the first image acquisition device, or randomly determined, which is not limited in the embodiment of the present application.

[0105] The laser radar 204 can emit light beams to the target base station and various objects in the environment where the target base station is located at different times to respectively measure the distance between the target base station and various objects in the environment where the target base station is located and the laser radar, and generate first point cloud data based on the distance between the target base station and various objects in the environment where the target base station is located and the laser radar and send it to the server 202.

[0106] After receiving the first image set and the first point cloud data, server 202 may determine a sparse depth map corresponding to each image in the first image set, as well as the pose of the first image acquisition device when each image was captured, based at least on the intrinsic parameters of the first image acquisition device, the first point cloud data, and the first image set. Subsequently, server 202 may determine antenna engineering parameters of the target base station based on the sparse depth map corresponding to each image in the first image set and the pose of the first image acquisition device when each image was captured.

[0107] In an embodiment of the present application, the first image acquisition device 203 and the laser radar 204 in Figure 2 can be integrated into one data acquisition device.

[0108] The embodiments of the present application do not limit the number of first image acquisition devices and the number of laser radars included in the data acquisition equipment. For example, the number of first image acquisition devices can be 1, 2, 3 or more, and the number of laser radars can be 1, 2, 3 or more.

[0109] The embodiments of the present application do not limit the position of the first image acquisition device included in the data acquisition device and the installation position of the laser radar. For example, the first image acquisition device can be located at the head of the data acquisition device or at the tail of the data acquisition device, and the laser radar can be located at the head of the data acquisition device or at the tail of the data acquisition device.

[0110] Figure 3 is a schematic diagram of the structure of a data acquisition device including two laser radars and three first image acquisition devices. As shown in Figure 3, the two laser radars are laser radar 204-a located at the head of the data acquisition device, and laser radar 204-b located at the rear of the data acquisition device. The three first image acquisition devices are first image acquisition device 203-a located at the head of the data acquisition device, first image acquisition device 203-b located at the upper side of the data acquisition device, and first image acquisition device 203-c located at the lower side of the data acquisition device.

[0111] In an embodiment of the present application, the first image acquisition device 203 and the laser radar 204 can be fixed in the data acquisition device by a magnetic bracket.

[0112] In embodiments of the present application, when multiple laser radars are included, the types of the respective laser radars may be the same or different. For example, as shown in FIG3 , laser radar 204-a and laser radar 204-b. In some embodiments, laser radar 204-a and laser radar 204-b may both be surround-view laser radars, or laser radar 204-a and laser radar 204-b may both be area array laser radars. In other embodiments, laser radar 204-a may be a surround-view laser radar, and laser radar 204-b may be an area array laser radar.

[0113] Optionally, the point cloud data generated by the surround-view lidar and the area array lidar can not only be used to reconstruct the environment in which the target base station is located, but can also be used to achieve positioning in scenarios where the global positioning system (GPS) is limited, or to enrich the point cloud data.

[0114] In the embodiment of the present application, when multiple first image acquisition devices are included, for any antenna of the target base station, the installation angle of each first image acquisition device should meet the following conditions:

[0115] Condition 1: Each first image acquisition device can capture at least two photos of the antenna within its own viewing angle.

[0116] Condition 2: The distance between the first image acquisition device and the antenna during shooting is less than or equal to the clear imaging distance of the first image acquisition device.

[0117] In some embodiments, the following constraints 1, 2, 3, and 4 can be used to ensure that the installation angles of the first image acquisition devices meet the above-mentioned conditions 1 and 2.

[0118] (Constraint 1)

[0119] (Constraint 2)

[0120] (Constraint 3)

[0121] (Constraint 4)

[0122] The following will describe the parameters in Constraints 1, 2, 3, and 4 in conjunction with Figure 4. As shown in Figure 4, O represents the position of the first image acquisition device, α0 is the horizontal angle at which the first image acquisition device is installed, β0 is the pitch angle at which the first image acquisition device is installed, f is the field of view of the first image acquisition device, d represents the horizontal and vertical distance between the position of the first image acquisition device and the target base station, and c min represents the minimum interval between two adjacent images, that is, the shortest distance the first image acquisition device needs to travel when capturing two adjacent images; α is the horizontal angle between the line connecting the first image acquisition device and the target base station and the direction of travel of the data acquisition device; β is the vertical angle between the antenna at a height of h on the target base station and the first image acquisition device; S max Indicates the clear imaging distance of the first image acquisition device.

[0123] For example, in one embodiment, assuming that the installation location of the first image acquisition device is consistent with that shown in FIG3 , and the horizontal and vertical distances d between the first image acquisition device and the target base station are between 5 and 50 meters, and the antenna height h is between 8 and 30 meters, then, through the calculations based on Constraints 1, 2, 3, and 4, the horizontal angle α0 of the first image acquisition device 203-a shown in FIG3 can be set to 12°, and the elevation angle β0 of the first image acquisition device 203-a can be set to 12°, to suit the imaging of antennas closer to the data acquisition equipment. The horizontal angle α0 of the first image acquisition device 203-b shown in FIG3 can be set to 45°, and the elevation angle β0 of the first image acquisition device 203-b can be set to 12°, to suit the imaging of antennas at lower elevations. The horizontal angle α0 of the first image acquisition device 203-c shown in FIG3 can be set to 45°, and the elevation angle β0 of the first image acquisition device 203-b can be set to 32°, to suit the imaging of antennas at higher elevations.

[0124] The arrangement of the first image acquisition device in this technical solution not only maximizes the capture of base station antenna information during the acquisition process, but also avoids tedious operations such as drone circumnavigation, allowing for rapid and accurate subsequent base station modeling. Testing has shown that the completeness of base station models created using this approach can reach over 80%.

[0125] In some embodiments, the data acquisition device can respond to a user's data acquisition request for the area to be measured and travel on the area to be measured at a preset speed. During the driving process of the data acquisition device, the telephoto camera can take long-distance photos of the antenna of the target base station at different shooting times to obtain a first image set containing multiple images. The laser radar can emit light beams to the target base station and various objects in the environment where the target base station is located at different times to respectively measure the distance between the target base station and various objects in the environment where the target base station is located and the laser radar, and generate first point cloud data based on the distance between the target base station and various objects in the environment where the target base station is located and the laser radar.

[0126] In the embodiment of the present application, there is no limitation on the preset speed, for example, 30 km / h.

[0127] In an optional embodiment, the drive test acquisition system 201 shown in Figure 2 may also include a second image acquisition device. Figure 5 illustrates another application scenario of an antenna engineering parameter determination system. As shown in Figure 5, the antenna engineering parameter determination system comprises the drive test acquisition system 201 and a server 202. The drive test acquisition system 201 may include a first image acquisition device 203, a second image acquisition device 501, and a lidar 204.

[0128] The second image acquisition device 501 can acquire panoramic images of the environment where the target base station is located, including the target base station, at different shooting moments to obtain a panoramic image set including multiple panoramic images.

[0129] In the embodiment of the present application, the second image acquisition device 501 is a camera whose imaging viewing angle can cover the entire sphere, or at least can cover an annular field of view on the horizontal plane, such as a panoramic camera (omnidirectional camera).

[0130] In an embodiment of the present application, the first image acquisition device 203, the laser radar 204 and the second image acquisition device 501 in Figure 5 can be integrated into one data acquisition device.

[0131] The embodiment of the present application does not limit the second image acquisition device included in the data acquisition device. For example, the number of the second image acquisition devices can be 1, 2, 3 or more.

[0132] The embodiment of the present application does not limit the position of the second image acquisition device included in the data acquisition device and the installation position of the laser radar. For example, the second image acquisition device can be located at the head of the data acquisition device or at the tail of the data acquisition device.

[0133] Figure 6 is a schematic diagram of the structure of another data acquisition device. As shown in Figure 6, the data acquisition device can be deployed with a second image acquisition device, two laser radars, and three first image acquisition devices. The second image acquisition device is a second image acquisition device 501 located at the top of the data acquisition device. The two laser radars are a laser radar 204-a located at the head of the data acquisition device and a laser radar 204-b located at the rear of the laser radar. The three first image acquisition devices are a first image acquisition device 203-a located at the front of the data acquisition device, a first image acquisition device 203-b located above the side of the data acquisition device, and a first image acquisition device 203-c located below the side of the data acquisition device.

[0134] In an optional embodiment, the antenna working parameter determination system shown in FIG2 and the antenna working parameter determination system shown in FIG5 may further include a satellite navigation device (global navigation satellite system, GNSS) for determining the geographic location of the drive test collection system at different times.

[0135] Correspondingly, the GNSS can also be fixed to the data acquisition device via a magnetic bracket, such as the GNSS301 shown in Figure 3 or Figure 6.

[0136] The antenna engineering parameter determination system provided in the embodiments of the present application may also include an artificial intelligence (AI) entity, which may be an AI network element or an AI module. The embodiments of the present application are not limited to this. A neural network model may be deployed in the AI ​​entity, and AI-related operations such as constructing a training dataset and training the model may be performed.

[0137] In some embodiments, the AI ​​entity can be integrated into the server 202 shown in Figure 2, so that the server 202 can process the data through the AI ​​entity in the server 202, obtain corresponding processing results, and send the processing results to the terminal device.

[0138] In some embodiments, the road test collection system 201 of the above-mentioned antenna engineering parameter determination system may also include one or more sensors, such as GPS / real-time kinematic (RTK) sensors and inertial measurement units (IMU) sensors, etc., which are not limited in this embodiment of the present application.

[0139] The following describes the antenna working parameter determination method provided in the embodiment of the present application in conjunction with the antenna working parameter determination system shown in FIG. 2 .

[0140] FIG7 is a schematic diagram of an interactive flow of a method for determining antenna parameters provided in an embodiment of the present application. The method is executed by the first image acquisition device, server, and laser radar shown in FIG2 . As shown in FIG7 , the method includes:

[0141] S701: A first image acquisition device sends a first image set to a server.

[0142] Each image in the first image set is taken by the first image acquisition device and contains an image of the antenna of the target base station.

[0143] The resolution of each image in the first image set is greater than a resolution threshold.

[0144] In an optional embodiment, the first image acquisition device may capture the antenna of the target base station at different capture times to obtain multiple images containing the antenna of the target base station, i.e., a first image set. The first image acquisition device may then send the first image set to the server.

[0145] S702: The laser radar sends first point cloud data to the server.

[0146] The first point cloud data may include point cloud data of the target base station and point cloud data of the scene where the target base station is located at multiple time moments.

[0147] The first point cloud data is point cloud data in the laser radar coordinate system.

[0148] In an optional embodiment, the laser radar can emit light beams to the target base station and various objects in the environment where the target base station is located at different times to obtain the distance between the target base station and the laser radar, as well as the distance between the laser radar and various objects in the environment where the target base station is located. Then, based on the distance between the target base station and the laser radar, as well as the distance between the laser radar and various objects in the environment where the target base station is located, point cloud data in the laser radar's coordinate system is generated, i.e., first point cloud data, and the first point cloud data is sent to the server.

[0149] S703, the server determines a sparse depth map corresponding to each image in the first image set and a posture of the first image acquisition device when taking each image based on the internal parameters of the first image acquisition device, the first point cloud data and the first image set.

[0150] Among them, the internal parameters of the first image acquisition device can be pre-stored in the server, or can be determined based on a preset internal parameter determination method, and the embodiment of the present application does not limit this.

[0151] In the embodiment of the present application, the preset internal parameter determination method may include but is not limited to the checkerboard calibration method. The specific implementation steps can refer to the relevant technology and will not be repeated here.

[0152] It can be understood that the internal parameter of the first image acquisition device is an essential feature of the first image acquisition device and generally does not change, so it only needs to be obtained once.

[0153] The sparse depth map corresponding to each image is used to indicate the distance between the first image acquisition device and the antenna in the image.

[0154] Specifically, after the server receives the first image set sent by the first image acquisition device and the first point cloud data sent by the lidar, it can first obtain the internal parameters of the first image acquisition device, and then determine the sparse depth map corresponding to each image in the first image set based on the internal parameters of the first image acquisition device, the first point cloud data and the first image set, as well as the posture of the first image acquisition device when taking each image.

[0155] Assume that the first image set includes a fifth image, that is, the fifth image can be any image in the first image set. The following uses the fifth image as an example to illustrate how the server determines the sparse depth map corresponding to the fifth image, as well as the position and posture of the first image acquisition device when capturing the fifth image. The server determines the sparse depth maps corresponding to the remaining images in the first image set, as well as the position and posture of the first image acquisition device when capturing the remaining images, in a manner similar to the method for determining the fifth image described below, and will not be further described here.

[0156] When determining the sparse depth map corresponding to the fifth image and the position of the first image acquisition device when capturing the fifth image, the server may refer to the method shown in FIG8 . As shown in FIG8 , the method includes:

[0157] S801, based on the first point cloud data, obtain a time-series pose sequence of the laser radar.

[0158] Among them, the time-series pose sequence of the lidar includes the pose of the lidar at each moment.

[0159] Specifically, after receiving the first point cloud data sent by the laser radar, the server can use the laser radar as the main body to determine the posture of the laser radar when collecting the first point cloud data at different times through a preset posture estimation algorithm to obtain the time-series posture sequence of the laser radar.

[0160] Among them, the preset pose estimation algorithm may include but is not limited to the GPS-IMU-Lidar SLAM algorithm, for example, the FAST-LIO algorithm, the LIO-SAM algorithm, etc., which is not limited in the embodiment of the present application.

[0161] S802, based on the time-series posture sequence of the laser radar and the fifth image, determine the posture of the first image acquisition device when taking the fifth image.

[0162] In an optional embodiment, the server may first take the posture of the lidar at at least one moment adjacent to the timestamp of the fifth image in the temporal posture sequence as the first target posture, and then determine the posture of the first image acquisition device when taking the fifth image based on the first target posture and the relative external parameters of the first image acquisition device and the lidar.

[0163] The timestamp of the fifth image is used to indicate the time when the fifth image is captured.

[0164] The relative external parameters of the first image acquisition device and the laser radar can be obtained by matching the edge contour of the same marker contained in the image taken by the first image acquisition device and the point cloud data. The specific steps can be referred to the relevant technology and will not be repeated here.

[0165] It should be noted that when the phase position of the first image acquisition device and the laser radar does not change, the relative external parameters of the first image acquisition device and the laser radar will not change either. Therefore, when the phase position of the first image acquisition device and the laser radar does not change, the relative external parameters of the first image acquisition device and the laser radar need to be obtained once.

[0166] The at least one moment adjacent to the timestamp of the fifth image may include two moments or three moments. The embodiment of the present application does not limit this. The following explanation is given by taking the example of at least one moment adjacent to the timestamp of the fifth image including two moments.

[0167] Specifically, in some embodiments, after obtaining the time-series pose sequence of the lidar, the server may first use the poses at the two moments in the time-series pose sequence closest to the moment when the fifth image was captured as the first target pose. The server may then perform linear interpolation on the first target pose and then multiply the linearly interpolated first target pose by the relative extrinsic parameter of the first image acquisition device and the lidar to obtain the pose of the first image acquisition device when the fifth image was captured.

[0168] S803: Determine a sparse depth map corresponding to the fifth image based on the posture of the first image acquisition device and the internal parameters of the first image acquisition device when capturing the fifth image.

[0169] In an optional embodiment, the server can first convert the first point cloud data into second point cloud data in the world coordinate system based on the time-series posture sequence of the lidar, and then process the second point cloud data based on the posture of the first image acquisition device when taking the fifth image to obtain point cloud data corresponding to the fifth image, and finally determine the sparse depth map corresponding to the fifth image based on the posture of the first image acquisition device when taking the fifth image and the point cloud data corresponding to the fifth image.

[0170] Specifically, in some embodiments, the server can first convert the first point cloud data into point cloud data in the world coordinate system based on the time-series posture sequence of the lidar, and perform noise filtering on the point cloud data in the world coordinate system to obtain second point cloud data, and then based on the posture of the first image acquisition device when taking the fifth image, process the second point cloud data through a preset hidden point removal (HPR) algorithm to obtain point cloud data corresponding to the fifth image.

[0171] Afterwards, the server can determine the sparse depth map corresponding to the fifth image based on the posture of the first image acquisition device when taking the fifth image, the point cloud data corresponding to the fifth image, and the internal parameters of the first image acquisition device.

[0172] In an optional embodiment, after obtaining the first image set and the first point cloud data, the server can sort the images in the first image set according to their timestamps, and sort the point cloud data at multiple moments in the first point cloud data according to the point cloud data at different moments. This allows the server to quickly retrieve images or point cloud data from the first image set at a specific moment based on the timestamps, thereby increasing the speed of determining antenna engineering parameters.

[0173] S704: The server determines the antenna parameters of the target base station based on the sparse depth map corresponding to each image in the first image set and the posture of the first image acquisition device when each image is taken.

[0174] In an optional implementation, the server may determine the antenna parameters of the target base station by referring to the method shown in FIG9 . As shown in FIG9 , the method includes:

[0175] S901, for each image in the first image set, the server determines the three-dimensional coordinates of at least one pixel point contained in the target area of ​​the image in the world coordinate system based on the sparse depth map of the image and the posture of the first image acquisition device when taking the image.

[0176] The target area of ​​each image can be determined based on the corner points of the antenna in the image.

[0177] Specifically, after determining the sparse depth map corresponding to each image in the first image set and the position of the first image acquisition device when each image was captured, the server can first use a preset target detection model to identify the base station antennas contained in each image in the first image set, as well as the corner points of each antenna. For each image, the server can perform the following operations:

[0178] Connect the corner points contained in the image to obtain the target area of ​​the image. The server can then determine the depth value (i.e., pixel value) of at least one pixel contained in the target area of ​​the image based on the sparse depth map of the image. Then, for each pixel in the at least one pixel, the server can determine the three-dimensional coordinates of the pixel in the world coordinate system based on the depth value of the pixel and the position of the first image acquisition device when the image was captured.

[0179] By repeatedly performing the above steps, the server can obtain the three-dimensional coordinates of at least one pixel point contained in the target area of ​​each image in the first image set in the world coordinate system.

[0180] In an embodiment of the present application, the preset target detection model may include but is not limited to a Faster_RCNN model, a Cascade_RCNN model, a Yolo model, and an SSD model, etc., and the embodiment of the present application is not limited to this.

[0181] The preset target detection model can be obtained by training a preset initial model and images with antenna annotation data. The specific training process can refer to the model training process in the relevant technology and will not be repeated here. Among them, the preset initial model can include, but is not limited to, for example, an SSD model, a Cascade_RCNN model, etc., and this embodiment of the application does not limit this.

[0182] S902: The server determines, from the first image set, a plurality of second image sets including the same antenna based on the three-dimensional coordinates of at least one pixel point included in the target area of ​​each image in the world coordinate system.

[0183] In an optional implementation, after determining the three-dimensional coordinates of at least one pixel point contained in the target area of ​​each image in the first image set in the world coordinate system in S901, the server may perform the following operations for each image:

[0184] First, based on the three-dimensional coordinates of at least one pixel point contained in the target area of ​​the image in the world coordinate system, the three-dimensional coordinates of the center point of the target area of ​​the image are determined, and then based on the three-dimensional coordinates of the center point of the target area of ​​each image, at least one second image set containing the same antenna is determined from the first image set.

[0185] Assume that the first image set includes the third and fourth images. That is, the third and fourth images can be any two images in the first image set. The following describes whether the third and fourth images contain the same antenna. The process for determining whether the remaining images in the first image set contain the same antenna can be referenced to the process for determining whether the third and fourth images contain the same antenna, and is not further described here.

[0186] Specifically, the server can determine the three-dimensional coordinates of the center point of the target area of ​​the third image based on the three-dimensional coordinates of at least one pixel point contained in the target area of ​​the third image in the world coordinate system, and determine the three-dimensional coordinates of the center point of the target area of ​​the fourth image based on the three-dimensional coordinates of at least one pixel point contained in the target area of ​​the fourth image in the world coordinate system.

[0187] The server may then determine a relative distance between the center point of the target area in the third image and the center point of the target area in the fourth image based on the three-dimensional coordinates of the center point of the target area in the third image and the three-dimensional coordinates of the center point of the target area in the fourth image. If the relative distance is less than a distance threshold, the server may determine that the third image and the fourth image contain the same antenna and that the third image and the fourth image belong to the same second image set.

[0188] In the embodiment of the present application, the distance threshold may be the minimum installation distance between antennas, or the average installation distance between antennas, which is not limited in the embodiment of the present application.

[0189] For example, assuming the target area of ​​the third image contains three pixels, m, n, and p, and the target area of ​​the fourth image contains three pixels, x, o, and d, the server can determine the three-dimensional coordinates of the center point q1 of the target area of ​​the third image based on the three-dimensional coordinates of the three pixels m, n, and p in the world coordinate system, and determine the three-dimensional coordinates of the center point q2 of the target area of ​​the third image based on the three-dimensional coordinates of the three pixels x, o, and d in the world coordinate system. The server can then determine the relative distance f between the center points q1 and q2 based on the three-dimensional coordinates of q1 and q2. If the relative distance f is less than the distance threshold σ, the server can determine that the third and fourth images contain the same antenna and that the third and fourth images belong to the same second image set.

[0190] S903, for each second image set, the server can determine at least two images from the second image set, and for the same corner point in the at least two images, based on the two-dimensional coordinates of the corner point in the image coordinate system and the posture of the first image acquisition device when taking each of the at least two images, determine the three-dimensional coordinates of the corner point in the world coordinate system, and obtain the three-dimensional coordinates of each corner point of the antenna in the second image set in the world coordinate system.

[0191] Specifically, after obtaining multiple second image sets in S902, the server may perform the following operations for each second image set:

[0192] At least two images are determined from the second image set, and the relative positions of the at least two images are determined based on the position of the first image acquisition device when each of the at least two images is captured. Then, for the same corner point contained in the at least two images, the two-dimensional coordinates of the corner point in the image coordinate system are determined, and the three-dimensional coordinates of the corner point in the world coordinate system are determined through a preset algorithm.

[0193] The preset algorithm may include but is not limited to epipolar constraint algorithms, and the embodiments of the present application do not limit this.

[0194] In the above manner, the three-dimensional coordinates of each corner point of the antenna in each second image set in the world coordinate system can be obtained.

[0195] The above-mentioned at least two images may include two images or three images. The embodiment of the present application does not limit this. The following takes the at least two images including the first image and the second image, the preset algorithm is the epipolar constraint, and the corner point n1 included in the first image and the corner point n2 included in the second image are the same corner point as an example to illustrate the process of the server determining the three-dimensional coordinates of the corner point n1 (or corner point n2) in the world coordinate system.

[0196] A schematic diagram of performing epipolar constraints on the first image and the second image is shown in FIG10 , where O1 is the position where the first image is captured when the first image is taken, O2 is the position where the first image is captured when the second image is taken, P is a point in three-dimensional space, and the projection of P on the first image is P1, and the projection on the second image is P2.

[0197] Specifically, the server can first determine the relative position between the first image and the second image based on the position of the first image acquisition device when shooting the first image and the position of the first image acquisition device when shooting the second image, and then determine the depth value of the corner point A in the world coordinate system based on the two-dimensional coordinates of the corner point A in the image coordinate system of the first image, the two-dimensional coordinates of the corner point A in the image coordinate system of the second image, and the relative position between the first image and the second image using the following formula 1. s1p1=s2R*p2+t (Formula 1)

[0198] Wherein, s1 is the depth value of corner point n1, p1 is the two-dimensional coordinate of corner point n1 in the image coordinate system of the first image, s2 is the depth value of corner point n2, p2 is the two-dimensional coordinate of corner point n2 in the image coordinate system of the second image, R represents the rotation value in the relative posture between the first image and the second image, and t represents the displacement value in the relative posture between the first image and the second image.

[0199] After the depth value of each corner point is determined in the above manner, the three-dimensional coordinates of each corner point can be obtained according to the two-dimensional coordinates of each corner point in the image coordinate system and the depth value.

[0200] S904: The server determines the antenna engineering parameters of each antenna based on the three-dimensional coordinates of each corner point of each antenna in the world coordinate system, and obtains the antenna engineering parameters of the target base station.

[0201] In an optional implementation manner, for each antenna, the server may perform the following operations:

[0202] Based on the three-dimensional coordinates of each corner point of the antenna, the corner points of the antenna are classified to obtain N types of corner points. Then, the center point of each type of corner point is used as the target corner point of the antenna to obtain N target corner points. Finally, based on the three-dimensional coordinates of the N target corner points, the antenna working parameters of the antenna are determined.

[0203] Wherein, N is a positive integer.

[0204] In the embodiment of the present application, N can be determined according to the actual number of corner points of the antenna. For example, when the actual number of corner points of the antenna is 4, N can be set to 4. The following description takes N as 4 as an example.

[0205] In an embodiment of the present application, the antenna engineering parameters may include but are not limited to the azimuth and downtilt angles of the antenna, as well as parameters such as the longitude and latitude and hanging height of the antenna. The following explanation is given by taking the example that the antenna engineering parameters may include the azimuth, downtilt angle, longitude and latitude and hanging height of the antenna.

[0206] Specifically, after obtaining the three-dimensional coordinates of the corner points in each second image set in S903, the server may classify the three-dimensional coordinates of the corner points in each second image set using a preset clustering algorithm to obtain four categories of corner points. The server may then delete outliers from each category of corner points and, for each category of corner points, determine the center point of that category, i.e., the target corner point, based on the three-dimensional coordinates of the deleted corner points and the preset clustering algorithm. Finally, the server may obtain four target corner points in each second image set.

[0207] The server can determine the 3D coordinates of the center point of the antenna in each second image set based on the 3D coordinates of the four target corner points in each second image set. The server then determines the latitude, longitude, and height of the antenna in the second image set based on the 3D coordinates of the center point. Furthermore, the server uses a preset plane fitting algorithm to determine the plane containing the four target corner points in the second image set. Furthermore, the server determines the azimuth and downtilt angles of the antenna in the second image set based on the normal vectors of the plane containing the four target corner points, thereby obtaining the antenna engineering parameters of the target base station.

[0208] In the embodiment of the present application, the preset clustering algorithm may include but is not limited to the k-menas algorithm, such as the DBSCAN clustering algorithm, etc., and the embodiment of the present application does not limit this.

[0209] It can be seen from the above technical solution that in the embodiment of the present application, when determining the antenna engineering parameters of the target base station, it is only necessary to use a first image acquisition device, a laser radar and a server to realize the survey of the antenna engineering parameters of the target base station without the need to use a drone for shooting. Therefore, it can effectively solve the problems of high cost and low efficiency caused by drones in related technologies.

[0210] In addition, when determining antenna parameters, the embodiment of the present application is based on the sparse depth map corresponding to each image in the first image set and the position of the first image acquisition device when each image in the first image set was captured, to restore the antenna corner points from two-dimensional coordinates to three-dimensional coordinates, and then to survey the antenna parameters using the three-dimensional coordinates of the antenna corner points. Therefore, in the embodiment of the present application, the key is to ensure the clarity of each image in the first image set, that is, to meet the high quality requirements for the image, without having to determine the antenna parameters of each antenna on the base station based on the three-dimensionally reconstructed base station. Therefore, there is no need to use photos from multiple perspectives to perform three-dimensional reconstruction of the base station, thereby effectively avoiding the problem of inaccurate antenna parameters caused by the limited perspective of the photos in the related art.

[0211] The following will provide a detailed interactive flow diagram of the method for determining antenna parameters by combining the contents of Figures 7, 8, and 9. As shown in Figure 11, the method includes:

[0212] S1101: A first image acquisition device sends a first image set to a server.

[0213] For details, please refer to S701 and will not be repeated here.

[0214] S1102, the laser radar sends first point cloud data to the server.

[0215] For details, please refer to S702 and will not be repeated here.

[0216] S1103: The server obtains a temporal pose sequence of the laser radar based on the first point cloud data.

[0217] For details, please refer to S801 and will not be repeated here.

[0218] S1104, the server determines the posture of the first image acquisition device when taking each image in the first image set based on the time-series posture sequence of the laser radar and each image in the first image set.

[0219] For details, please refer to S802 and will not be repeated here.

[0220] S1105 , determining a sparse depth map corresponding to each image in the first image set based on the posture of the first image acquisition device when capturing each image in the first image set and the internal parameters of the first image acquisition device.

[0221] For details, please refer to S803 and will not be repeated here.

[0222] S1106, for each image in the first image set, the server determines the three-dimensional coordinates of at least one pixel point contained in the target area of ​​the image in the world coordinate system based on the sparse depth map of the image and the posture of the first image acquisition device when taking the image.

[0223] For details, please refer to S901 and will not be repeated here.

[0224] S1107: The server determines, from the first image set, a plurality of second image sets including the same antenna based on the three-dimensional coordinates of at least one pixel point included in the target area of ​​each image in the world coordinate system.

[0225] For details, please refer to S902 and will not be repeated here.

[0226] S1108, for each second image set, the server can determine at least two images from the second image set, and for the same corner point in the at least two images, based on the two-dimensional coordinates of the corner point in the image coordinate system and the posture of the first image acquisition device when taking each of the at least two images, determine the three-dimensional coordinates of the corner point in the world coordinate system, and obtain the three-dimensional coordinates of each corner point of the antenna in the second image set in the world coordinate system.

[0227] For details, please refer to S903 and will not be repeated here.

[0228] S1109: The server determines the antenna engineering parameters of each antenna based on the three-dimensional coordinates of each corner point of each antenna in the world coordinate system, and obtains the antenna engineering parameters of the target base station.

[0229] For details, please refer to S904 and will not be repeated here.

[0230] The following describes the antenna working parameter determination method provided in the embodiment of the present application in conjunction with the antenna working parameter determination system shown in FIG5 .

[0231] FIG12 is a schematic diagram of an interactive process of a method for determining antenna parameters provided in an embodiment of the present application. The method is executed by the first image acquisition device, the second acquisition device, the server, and the laser radar shown in FIG5 . As shown in FIG12 , the method includes:

[0232] S1201: A first image acquisition device sends a first image set to a server.

[0233] The specific implementation method can be referred to S701 and will not be described in detail here.

[0234] S1202, the laser radar sends first point cloud data to the server.

[0235] The specific implementation method can be referred to S702 and will not be repeated here.

[0236] S1203: The second image acquisition device sends a panoramic image set to the server.

[0237] A panoramic image set contains multiple panoramic images.

[0238] Each panoramic image in the panoramic image set is taken by the second image acquisition device and contains an image of the target base station and the environment in which the target base station is located.

[0239] In an optional embodiment, the second image acquisition device may capture the target base station and its surroundings at different capture times to obtain multiple panoramic images of the target base station and its surroundings, i.e., a panoramic image set. The second image acquisition device may then transmit the panoramic image set to a server.

[0240] S1204, the server determines the sparse depth map corresponding to each image in the first image set and the posture of the first image acquisition device when taking each image based on the internal parameters of the first image acquisition device, the internal parameters of the second image acquisition device, the first point cloud data, the first image set and the panoramic image set.

[0241] The internal parameters of the second image acquisition device may be pre-stored in the server, or may be determined based on a preset internal parameter determination method, which is not limited in this embodiment of the present application.

[0242] It can be understood that the internal parameter of the second image acquisition device is an essential feature of the second image acquisition device and generally does not change, so it only needs to be obtained once.

[0243] In an optional embodiment, the server can determine the sparse depth map corresponding to each image in the first image set and the position of the first image acquisition device when each image is captured by the method shown in Figure 13. As shown in Figure 13, the method includes:

[0244] S1301: The server determines the position and posture of the second image acquisition device when taking each panoramic image based on the first point cloud data and the panoramic image set.

[0245] In an optional embodiment, the server can first obtain the time-series pose sequence of the lidar based on the first point cloud data, and then determine the pose of the second image acquisition device when taking each panoramic image based on the time-series pose sequence of the lidar and the panoramic image set.

[0246] Specifically, after receiving the first point cloud data sent by the laser radar, the server can use the laser radar as the main body to determine the pose of the laser radar when collecting the first point cloud data at different times through a preset pose estimation algorithm, thereby obtaining a time-series pose sequence of the laser radar. For each panoramic image, the server can first use the pose of at least one time in the time-series pose sequence of the laser radar that is adjacent to the time when the panoramic image was captured as the panoramic target pose. Then, based on the panoramic target pose and the relative external parameters of the second image capture device and the laser radar, the server can determine the pose of the second image capture device when the panoramic image was captured.

[0247] The relative external parameters of the second image acquisition device and the laser radar can be obtained by matching the edge contour of the same marker contained in the image taken by the second image acquisition device and the point cloud data. The specific steps can be referred to the relevant technology and will not be repeated here.

[0248] It should be noted that when the phase position of the second image acquisition device and the laser radar does not change, the relative external parameters of the second image acquisition device and the laser radar will not change either. Therefore, when the phase position of the second image acquisition device and the laser radar does not change, the relative external parameters of the second image acquisition device and the laser radar need to be obtained once.

[0249] For example, assuming that the panoramic image set includes panoramic image A, when determining the posture of the second image acquisition device when taking panoramic image A, the server can use the posture of at least one moment adjacent to the moment of taking panoramic image A in the time-series posture sequence of the lidar as the panoramic target posture, and then determine the posture of the second image acquisition device when taking panoramic image A based on the panoramic target posture and the relative external parameters of the second image acquisition device and the lidar.

[0250] S1302: The server determines a sparse depth map corresponding to each panoramic image based on the posture of the second image acquisition device when taking each panoramic image and the internal parameters of the second image acquisition device.

[0251] In an optional embodiment, the server can first convert the first point cloud data into second point cloud data in the world coordinate system based on the time-series posture sequence of the lidar, and then for each panoramic image, the server can process the second point cloud data based on the posture of the second image acquisition device when taking the panoramic image to obtain the point cloud data corresponding to the panoramic image, and finally determine the sparse depth map corresponding to the panoramic image based on the posture of the second image acquisition device when taking the panoramic image and the point cloud data corresponding to the panoramic image.

[0252] Specifically, in some embodiments, after converting the first point cloud data into point cloud data in a world coordinate system, the server may filter the point cloud data in the world coordinate system for noise to obtain second point cloud data. For each panoramic image, the server may process the second point cloud data using a preset HPR algorithm based on the position of the second image acquisition device when the panoramic image was captured, to obtain point cloud data corresponding to the panoramic image. The server may then determine a sparse depth map corresponding to the panoramic image based on the position of the second image acquisition device when the panoramic image was captured, the point cloud data corresponding to the panoramic image, and the internal parameters of the second image acquisition device.

[0253] In some embodiments, after obtaining the sparse depth map corresponding to each panoramic image in the above manner, the server can also identify the objects contained in each panoramic image (such as trees, buildings, street lights, etc.) through a preset target detection model to obtain the labels and two-dimensional coordinates of each object in each panoramic image, and then determine the labels and three-dimensional coordinates of each object contained in the panoramic image based on the sparse depth map corresponding to each panoramic image and the labels and two-dimensional coordinates of each object in each panoramic image, and model the target base station and the environment in which the target base station is located based on the second point cloud data in the world coordinate system, as well as the labels and three-dimensional coordinates of each object contained in the panoramic image.

[0254] Through the above technical solution, the target base station and the environment in which the target base station is located can be restored based on the sparse depth maps corresponding to multiple panoramic images and the point cloud data obtained by the lidar, without the need to determine the antenna working parameters of each antenna on the base station based on the three-dimensionally reconstructed base station. Therefore, there is no need to use photos from multiple perspectives to reconstruct the base station in three dimensions.

[0255] S1303, the server determines the sparse depth map corresponding to each image in the first image set and the pose of the first image acquisition device when capturing each panoramic image based on the intrinsic parameters of the first image acquisition device, the first image set, the pose of the second image acquisition device when capturing each panoramic image, the sparse depth map corresponding to each panoramic image, and the relative extrinsic parameters of the first image acquisition device and the second image acquisition device.

[0256] The relative external parameters of the first image acquisition device and the second image acquisition device can be obtained by matching the feature points corresponding to the landmarks contained in the image taken by the first image acquisition device and the image taken by the second image acquisition device. The specific steps can be referred to the relevant technology and will not be repeated here.

[0257] It should be noted that when the phase position of the first image acquisition device and the second image acquisition device does not change, the relative extrinsic parameters of the first image acquisition device and the second image acquisition device will not change either. Therefore, when the phase position of the first image acquisition device and the second image acquisition device does not change, the relative extrinsic parameters of the first image acquisition device and the second image acquisition device only need to be obtained once.

[0258] Assuming that the first image set includes the sixth image, the following will take the sixth image as an example to introduce how the server determines the posture of the first image acquisition device when shooting the sixth image, and the sparse depth map corresponding to the sixth image. The process of determining the sparse depth maps corresponding to the remaining images in the first image set, and the posture of the first image acquisition device when shooting the remaining images can refer to the following process of determining the sparse depth map corresponding to the sixth image, and the posture of the first image acquisition device when shooting the sixth image, which will not be repeated here.

[0259] Specifically, the server first uses the pose of the second image acquisition device at at least one time instant adjacent to the timestamp of the sixth image as a second target pose from the pose of the second image acquisition device when capturing each panoramic image. The server then determines the pose of the first image acquisition device when capturing the sixth image based on the second target pose and the relative extrinsic parameters of the first and second image acquisition devices. The server can then determine a sparse depth map corresponding to the sixth image based on the pose of the first image acquisition device when capturing the sixth image and the sparse depth map corresponding to the target panoramic image.

[0260] The timestamp of the sixth image is used to indicate the time when the sixth image is captured.

[0261] The target panoramic image includes at least one panoramic image corresponding to the second target posture.

[0262] The at least one moment adjacent to the timestamp of the sixth image may include two moments or three moments. The following description will be made by taking the example that the at least one moment adjacent to the timestamp of the sixth image includes two moments.

[0263] The server first selects the poses of the second image acquisition device at the two moments closest to the timestamp of the sixth image from the poses of the second image acquisition device when capturing each panoramic image as the second target pose. Assuming that the second target poses include pose a and pose b, the server can perform linear interpolation on pose a and pose b to obtain a linearly interpolated pose. The server can then multiply the linearly interpolated pose with the relative extrinsic parameters of the first and second image acquisition devices to obtain the pose of the first image acquisition device when capturing the sixth image.

[0264] After obtaining the pose of the first image acquisition device when capturing the sixth image in the above manner, the server can determine the target panoramic image from the panoramic images corresponding to pose a and pose b (i.e., the second target pose), and project the sparse depth map corresponding to the target panoramic image into a point cloud. Then, based on the sixth image, the server processes the point cloud data of the sparse depth map corresponding to the target panoramic image using a preset HPR algorithm to obtain point cloud data corresponding to the sixth image. Finally, the server can project the point cloud data corresponding to the sixth image into a sparse depth map corresponding to the sixth image.

[0265] In an optional embodiment, after obtaining the panoramic image set, the server can sort the panoramic images contained in the panoramic image set according to the timestamps of each panoramic image in the panoramic image set, so that when the server subsequently calls a panoramic image in the panoramic image set at a certain moment, it can quickly call it through the timestamp, thereby improving the rate of determining the antenna working parameters.

[0266] S1205: The server determines the antenna parameters of the target base station based on the sparse depth map corresponding to each image in the first image set and the posture of the first image acquisition device when each image is taken.

[0267] The specific steps can refer to the method shown in FIG9 above, which will not be described again here.

[0268] The above technical solution determines antenna engineering parameters based on the sparse depth map corresponding to each image in the first image set and the position of the first image acquisition device when each image was captured. The sparse depth map corresponding to each image and the position of the first image acquisition device when each image was captured can be determined based on the intrinsic parameters of the first image acquisition device, the intrinsic parameters of the second image acquisition device, the first point cloud data acquired by the lidar, the first image set acquired by the first image acquisition device, and the panoramic image set acquired by the second image acquisition device. It is not necessary to determine the antenna engineering parameters of each antenna on the base station based on the three-dimensionally reconstructed base station. Therefore, it is not necessary to use photos from multiple perspectives to perform three-dimensional reconstruction of the base station, thereby effectively avoiding the problem of inaccurate antenna engineering parameters caused by the limited perspective of the photos in the related art.

[0269] Figure 14 is a structural block diagram of an antenna working parameter determination system provided in an embodiment of the present application. As shown in Figure 14, the antenna working parameter determination system includes a data acquisition module 1401, a data processing module 1402, an antenna working parameter estimation module 1403 and a physical environment modeling module 1404.

[0270] Optionally, the data acquisition module 1401 is mainly used to obtain first point cloud data through a lidar, obtain a first image set through a first image acquisition device, obtain a panoramic image set through a second image acquisition device, obtain location information through a GNSS, and obtain sensor data through a sensor, etc., and send the collected first point cloud data, first image set, panoramic image set, location information, sensor data, etc. to the data processing module 1402.

[0271] Optionally, the data processing module 1402 can determine parameter information such as the internal parameters of the first image acquisition device, the internal parameters of the second acquisition device, the relative external parameters between the first image acquisition device and the laser radar, the relative external parameters between the second image acquisition device and the laser radar, and the relative external parameters between the first image acquisition device and the second image acquisition device through a preset internal parameter determination method, and send each parameter information to the antenna engineering parameter estimation module 1403 and the physical environment modeling module 1404.

[0272] Antenna parameter estimation module 1403 may include a first determination module and a second determination module. The first determination module may determine a sparse depth map corresponding to each image in the first image set and the position of the first image acquisition device when each image was captured. The second determination module may determine the antenna parameters of the target base station based on the sparse depth map corresponding to each image in the first image set and the position of the first image acquisition device when each image was captured.

[0273] Optionally, the physical environment modeling module 1404 can identify objects (such as trees, buildings, streetlights, etc.) contained in the panoramic images using a preset target detection model, obtain the two-dimensional coordinates of each object contained in each panoramic image, and obtain the three-dimensional coordinates of the objects contained in the panoramic images based on the two-dimensional labels corresponding to each panoramic image and the sparse depth map corresponding to each panoramic image. Subsequently, the physical environment modeling module 1404 can model the target base station and the environment in which the target base station is located based on the second point cloud data in the world coordinate system and the three-dimensional coordinates of the objects contained in the panoramic images.

[0274] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the interaction between various network elements. Accordingly, the embodiment of the present application also provides an antenna working parameter determination device, which is used to implement the above various methods. It can be understood that in order to implement the above functions, the antenna working parameter determination device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of the various examples described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in hardware or in a computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0275] In the embodiments of the present application, the antenna engineering parameter determination device can be divided into functional modules based on the above-mentioned method embodiments. For example, each functional module can be divided according to each function, or two or more functions can be integrated into a single processing module. The above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. It should be understood that the module division in the embodiments of the present application is illustrative and is merely a logical functional division. In actual implementation, other division methods may be used.

[0276] For example, taking the antenna engineering parameter determination device as the server in the above method embodiment as an example, the server at least includes the first determination module 1501 and the second determination module 1502 shown in FIG15 .

[0277] Among them, the first determination module 1501 is used to determine the sparse depth map corresponding to each image in the first image set, as well as the posture of the first image acquisition device when taking each image, based at least on the internal parameters of the first image acquisition device, the first point cloud data and the first image set.

[0278] The second determination module 1502 is used to determine the antenna parameters of the target base station based on the sparse depth map corresponding to each image in the first image set and the posture of the first image acquisition device when taking each image.

[0279] In the embodiments of the present application, the server is presented in the form of various functional modules divided in an integrated manner. The "module" here can refer to a specific application-specific integrated circuit (ASIC), a processor and memory that executes one or more software or firmware programs, an integrated logic circuit, and / or other devices that can provide the above functions.

[0280] Since the server provided in the embodiment of the present application can execute the above-mentioned antenna engineering parameter determination method, the technical effects that can be obtained can be referred to the above-mentioned method embodiment and will not be repeated here.

[0281] It should be understood that one or more of the above modules or units can be implemented by software, hardware, or a combination of the two. When any of the above modules or units is implemented in software, the software exists in the form of computer program instructions and is stored in a memory, and a processor can be used to execute the program instructions and implement the above method flow. The processor can be built into an SoC (system on chip) or an ASIC, or it can be an independent semiconductor chip. In addition to the core used to execute software instructions to perform calculations or processing within the processor, it can further include necessary hardware accelerators, such as field programmable gate arrays (FPGAs), PLDs (programmable logic devices), or logic circuits that implement dedicated logic operations.

[0282] When the above modules or units are implemented in hardware, the hardware can be any one or any combination of a CPU, a microprocessor, a digital signal processing (DSP) chip, a microcontroller unit (MCU), an artificial intelligence processor, an ASIC, a SoC, an FPGA, a PLD, a dedicated digital circuit, a hardware accelerator or a non-integrated discrete device, which can run the necessary software or not rely on the software to execute the above method flow.

[0283] Optionally, an embodiment of the present application further provides an antenna working parameter determination device (for example, the antenna working parameter determination device may be a chip or a chip system), and the antenna working parameter determination device includes a processor for implementing the method in any of the above method embodiments. In one possible design, the antenna working parameter determination device also includes a memory. The memory is used to store necessary program instructions and data, and the processor can call the program code stored in the memory to instruct the antenna working parameter determination device to execute the method in any of the above method embodiments. Of course, the memory may not be in the antenna working parameter determination device. When the antenna working parameter determination device is a chip system, it may be composed of a chip, or it may include a chip and other discrete devices, and the embodiment of the present application does not specifically limit this.

[0284] In one possible implementation, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program or instruction. When the computer program or instruction is run on an antenna engineering parameter determination device, the antenna engineering parameter determination device can execute the method described in any of the above method embodiments or any of its implementations.

[0285] In a possible implementation, an embodiment of the present application further provides a distributed training system, which includes the access network device described in the above method embodiment, the core network device described in the above method embodiment, and the terminal device described in the above method embodiment.

[0286] In a possible implementation, an embodiment of the present application further provides a method for determining antenna engineering parameters, which includes the method described in any of the above method embodiments or any of its implementations.

[0287] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using a software program, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0288] Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. A computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid state drives (SSDs)).

[0289] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other variations of the disclosed embodiments by reviewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0290] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely illustrative of the present application as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, the present application is intended to include such modifications and variations as fall within the scope of the claims of the present application and their equivalents.

Claims

1. A method for determining antenna engineering parameters, characterized in that: A server applied to an antenna working parameter determination system, wherein the antenna working parameter determination system includes a first image acquisition device, a laser radar, and the server, and the method includes: Determining a sparse depth map corresponding to each image in the first image set and a pose of the first image acquisition device when each image was captured based at least on the intrinsic parameters of the first image acquisition device, the first point cloud data, and the first image set; each image in the first image set is an image captured by the first image acquisition device and includes an antenna of a target base station; the resolution of each image in the first image set is greater than a resolution threshold; the sparse depth map corresponding to each image is used to indicate a distance between the first image acquisition device and the antenna in the image; and the first point cloud data is point cloud data in the coordinate system of the laser radar; The antenna working parameters of the target base station are determined based on the sparse depth map corresponding to each image in the first image set and the posture of the first image acquisition device when each image is taken.

2. The method according to claim 1, characterized in that The determining of the antenna parameters of the target base station based on the sparse depth map corresponding to each image in the first image set and the posture of the first image acquisition device when each image is captured includes: For each image in the first image set, determining, based on a sparse depth map of the image and a position of the first image acquisition device when the image was captured, the three-dimensional coordinates of at least one pixel point contained in a target area of ​​the image in a world coordinate system; the target area of ​​each image is determined based on a corner point of an antenna in the image; Determining at least one second image set containing the same antenna from the first image set based on the three-dimensional coordinates of at least one pixel point contained in the target area of ​​each image in a world coordinate system; For each second image set, determining at least two images from the second image set, and for a common corner point in the at least two images, determining the three-dimensional coordinates of the corner point in a world coordinate system based on the two-dimensional coordinates of the corner point in the image coordinate system and the position of the first image acquisition device when each of the at least two images was captured, thereby obtaining the three-dimensional coordinates of each corner point of the antenna in the second image set in the world coordinate system; the first image is different from the second image; Based on the three-dimensional coordinates of each corner point of each antenna in the world coordinate system, the antenna engineering parameters of the antenna are determined to obtain the antenna engineering parameters of the target base station.

3. The method according to claim 2, characterized in that The at least two images include a first image and a second image; The determining of the three-dimensional coordinates of the corner point in the world coordinate system based on the two-dimensional coordinates of the corner point in the image coordinate system and the posture of the first image acquisition device when capturing each of the at least two images comprises: determining a relative posture between the first image and the second image based on a posture of the first image acquisition device when capturing the first image and a posture of the first image acquisition device when capturing the second image; Based on the two-dimensional coordinates of the corner point in the image coordinate system of the first image, the two-dimensional coordinates of the corner point in the image coordinate system of the second image, and the relative posture between the first image and the second image, the three-dimensional coordinates of the corner point in the world coordinate system are determined.

4. The method according to any one of claims 2 to 3, characterized in that The determining, from the first image set, at least one second image set including the same antenna based on the three-dimensional coordinates of at least one pixel point included in the target area of ​​each image in the world coordinate system comprises: Determining the three-dimensional coordinates of a center point of the target area of ​​each image based on the three-dimensional coordinates of at least one pixel point contained in the target area of ​​the image in a world coordinate system; At least one second image set containing the same antenna is determined from the first image set based on the three-dimensional coordinates of the center point of the target area of ​​each image.

5. The method according to claim 4, characterized in that The first image set includes a third image and a fourth image; The determining, from the first image set based on the three-dimensional coordinates of the center point of the target area of ​​each image, at least one second image set containing the same antenna comprises: determining a relative distance between the center point of the target area of ​​the third image and the center point of the target area of ​​the fourth image based on the three-dimensional coordinates of the center point of the target area of ​​the third image and the three-dimensional coordinates of the center point of the target area of ​​the fourth image; When the relative distance is less than a distance threshold, determining that the third image and the fourth image include a same antenna; It is determined that the third image and the fourth image belong to the same second image set.

6. The method according to any one of claims 2 to 5, characterized in that: The determining of antenna engineering parameters of the antenna based on the three-dimensional coordinates of each corner point of each antenna includes: For each antenna, classify each corner point in the antenna based on the three-dimensional coordinates of each corner point in the antenna to obtain N types of corner points; N is a positive integer; The center point of each type of corner point is used as the target corner point of the antenna to obtain N target corner points; Based on the three-dimensional coordinates of the N target corner points, antenna engineering parameters of the antenna are determined.

7. The method according to any one of claims 1 to 6, characterized in that The first image set includes a fifth image; The determining, based at least on the intrinsic parameters of the first image acquisition device, the first point cloud data, and the first image set, of a sparse depth map corresponding to each image in the first image set and a position of the first image acquisition device when capturing each image, includes: Based on the first point cloud data, a time-series pose sequence of the laser radar is obtained; the time-series pose sequence of the laser radar includes the pose of the laser radar at each moment; Determining, based on the time-series pose sequence of the laser radar and the fifth image, the pose of the first image acquisition device when taking the fifth image; Based on the posture of the first image acquisition device and the internal parameters of the first image acquisition device when taking the fifth image, a sparse depth map corresponding to the fifth image is determined.

8. The method according to claim 7, characterized in that The determining, based on the time-series pose sequence of the laser radar and the fifth image, the pose of the first image acquisition device when taking the fifth image includes: The pose at at least one moment adjacent to the timestamp of the fifth image in the time-series pose sequence of the laser radar is used as the first target pose; the timestamp of the fifth image is used to indicate the time when the fifth image was captured; Based on the first target posture and the relative external parameters of the first image acquisition device and the laser radar, the posture of the first image acquisition device when taking the fifth image is determined.

9. The method according to claim 7 or 8, characterized in that The determining, based on the posture of the first image acquisition device and the internal parameters of the first image acquisition device when capturing the fifth image, a sparse depth map corresponding to the fifth image includes: Based on the temporal pose sequence of the laser radar, converting the first point cloud data into second point cloud data in a world coordinate system; processing the second point cloud data based on the posture of the first image acquisition device when capturing the fifth image to obtain point cloud data corresponding to the fifth image; Based on the posture of the first image acquisition device when taking the fifth image and the point cloud data corresponding to the fifth image, a sparse depth map corresponding to the fifth image is determined.

10. The method according to any one of claims 1 to 9, characterized in that The first image acquisition device is a telephoto camera.

11. The method according to claim 1, wherein The antenna engineering parameter determination system further comprises a second image acquisition device; The determining, based at least on the intrinsic parameters of the first image acquisition device, the first point cloud data, and the first image set, of a sparse depth map corresponding to each image in the first image set and a position of the first image acquisition device when capturing each image, includes: Based on the internal parameters of the first image acquisition device, the internal parameters of the second image acquisition device, the first point cloud data, the first image set and the panoramic image set, determine the sparse depth map corresponding to each image in the first image set, as well as the posture of the first image acquisition device when taking each image; each panoramic image in the panoramic image set is taken by the second image acquisition device and contains an image of the target base station and the environment in which the target base station is located.

12. The method according to claim 11, characterized in that The determining, based on the internal parameters of the first image acquisition device, the internal parameters of the second image acquisition device, the first point cloud data, the first image set, and the panoramic image set, of a sparse depth map corresponding to each image in the first image set, and a position of the first image acquisition device when capturing each image, includes: determining, based on the first point cloud data and the panoramic image set, a position and posture of the second image acquisition device when capturing each panoramic image; Determining a sparse depth map corresponding to each panoramic image based on the pose of the second image acquisition device when capturing each panoramic image and an internal parameter of the second image acquisition device; Based on the intrinsic parameters of the first image acquisition device, the first image set, the posture of the second image acquisition device when taking each panoramic image, the sparse depth map corresponding to each panoramic image, and the relative extrinsic parameters of the first image acquisition device and the second image acquisition device, the sparse depth map corresponding to each image in the first image set and the posture of the first image acquisition device when taking each image are determined.

13. The method according to claim 12, characterized in that The determining, based on the first point cloud data and the panoramic image set, the position and posture of the second image acquisition device when capturing each panoramic image comprises: Based on the first point cloud data, a time-series pose sequence of the laser radar is obtained; the time-series pose sequence of the laser radar includes the pose of the laser radar at each moment; Based on the time-series pose sequence of the laser radar and the panoramic image set, the pose of the second image acquisition device when taking each panoramic image is determined.

14. The method according to claim 12 or 13, characterized in that The first image set includes a sixth image; The method of determining the sparse depth map corresponding to each image in the first image set and the pose of the first image acquisition device when capturing each panoramic image based on the intrinsic parameters of the first image acquisition device, the first image set, the pose of the second image acquisition device when capturing each panoramic image, the sparse depth map corresponding to each panoramic image, and the relative extrinsic parameters of the first image acquisition device and the second image acquisition device, includes: From the poses of the second image acquisition device when capturing each panoramic image, a pose at at least one time adjacent to the timestamp of the sixth image is used as a second target pose; the timestamp of the sixth image is used to indicate the time when the sixth image was captured; determining, based on the second target posture and relative extrinsic parameters of the first image acquisition device and the second image acquisition device, a posture of the first image acquisition device when capturing the sixth image; Based on the posture of the first image acquisition device when shooting the sixth image, and the sparse depth map corresponding to the target panoramic image, the sparse depth map corresponding to the sixth image is determined; the target panoramic image includes at least one panoramic image corresponding to the second target posture.

15. The method according to any one of claims 11 to 14, characterized in that: The second image acquisition device is a panoramic camera.

16. An antenna engineering parameter determination device, characterized in that: The device is located in a server of an antenna engineering parameter determination system, and includes: a first determination module configured to determine, based at least on an intrinsic parameter of the first image acquisition device, the first point cloud data, and the first image set, a sparse depth map corresponding to each image in the first image set, and a position of the first image acquisition device when each image was captured; each image in the first image set is captured by the first image acquisition device and includes an antenna of a target base station; the resolution of each image in the first image set is greater than a resolution threshold; the sparse depth map corresponding to each image is used to indicate a distance between the first image acquisition device and the antenna in the image; and the first point cloud data is point cloud data in a coordinate system of the laser radar; The second determination module is used to determine the antenna working parameters of the target base station based on the sparse depth map corresponding to each image in the first image set and the posture of the first image acquisition device when taking each image.

17. An antenna engineering parameter determination system, characterized in that: The system includes: a first image acquisition device, a laser radar and a server; The first image acquisition device is used to acquire a first image set; The laser radar is used to obtain first point cloud data; The server is used to execute the antenna engineering parameter determination method according to any one of claims 1 to 15.

18. A server, characterized in that: The server includes at least one processor coupled to at least one memory: The at least one processor is used to execute the computer program or instructions stored in the at least one memory, so that the server executes the antenna engineering parameter determination method according to any one of claims 1-15.

19. A computer-readable storage medium, characterized in that The method comprises a program code, which, when running on a computer or a processor, enables the computer or the processor to execute the antenna engineering parameter determination method according to any one of claims 1 to 15.

Images