WO2024055846A1

WO2024055846A1 - Base station antenna pose information exploration method, device and system, and storage medium

Info

Publication number: WO2024055846A1
Application number: PCT/CN2023/115973
Authority: WO
Inventors: 胡文鹏; 俞胜兵; 范国田; 张海; 武斌
Original assignee: 中兴通讯股份有限公司
Priority date: 2022-09-13
Filing date: 2023-08-30
Publication date: 2024-03-21
Also published as: CN117746261A

Abstract

Embodiments of the present disclosure provide a base station antenna pose information exploration method, device and system, and a storage medium. The method comprises: acquiring image information of a base station antenna collected by an unmanned aerial vehicle; according to a preset image recognition model and the image information, acquiring a position of the unmanned aerial vehicle where the unmanned aerial vehicle collects the image information, and relative space coordinate information of each vertex of the base station antenna, wherein the image recognition model is used for recognizing the relative space coordinate information of each vertex of the base station antenna comprised in the image information; and calculating pose information of the base station antenna according to the position of the unmanned aerial vehicle and the relative space coordinate information of each vertex of the base station antenna.

Description

A base station antenna position and attitude information exploration method, device, system and storage medium

Cross-references to related applications

This disclosure is based on the Chinese patent application 202211111722.5 with the invention title "A base station antenna pose information exploration method, device, system and storage medium" submitted on September 13, 2022, and claims the priority of this patent application, which is incorporated by reference. The entire disclosure is incorporated into this disclosure.

Technical Field

The embodiments of the present disclosure relate to the technical field of mobile communication base station antenna detection, and specifically, to a base station antenna pose information exploration method, device, system and storage medium.

Background technique

In recent years, communication technology has developed rapidly, and the exploration of base stations has become an important part of the construction and maintenance of base stations. The most commonly used methods for base station inspection, measurement, and resource acquisition are contact measurement and photography. Contact measurement includes but is not limited to the use of gyroscopes, inclinometers, rangefinders, etc. Base station antennas are often deployed at relatively high locations. Such as building roofs, iron towers, etc., the measurement process needs to be carried out by professional personnel in compliance with safety regulations. Therefore, the test process has very high construction requirements and environmental requirements. For example, strong winds, heavy rain, heavy snow, excessive temperatures, excessive temperatures, and other adverse weather conditions will prevent construction, which will affect the progress of the project, safety accidents, etc., and human factors It has a great influence on the measurement accuracy.

At present, the fixed-angle measurement method of a drone can also be used to photograph the side and diagonally above the antenna at a fixed angle, and then obtain the antenna boundary through image grayscale processing, which is also a measurement method. This method has certain requirements for the posture of the drone. When measuring the downtilt angle, the drone must be oriented directly to the side of the antenna and at a fixed position. When measuring the antenna direction angle, the drone must be oriented facing the front of the antenna. Therefore, during the measurement process, the requirements for the drone pilot and the weather environment are relatively high. Once there is a deviation, the measurement will be inaccurate and a certain error will occur. For example, when there is a little wind at a high place and the drone hovers inaccurately, There will be errors in measurement.

Contents of the invention

Embodiments of the present disclosure provide a base station antenna pose information exploration method, device, system and storage medium to at least solve the technical problem in related technologies that requires high UAV control during the measurement process.

According to an embodiment of the present disclosure, a base station antenna pose information exploration method is provided, including:

Obtain the image information of the base station antenna collected by the drone;

According to the preset image recognition model and the image information, the relative spatial coordinate information of each vertex of the base station antenna is obtained based on the position of the drone when collecting the image information; the image recognition model is used to identify The relative spatial coordinate information of each vertex of the base station antenna contained in the image information;

Calculate the pose information of the base station antenna based on the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna;

According to another embodiment of the present disclosure, a base station antenna pose information exploration device is provided, including:

The first acquisition module is configured to acquire the image information of the base station antenna collected by the drone;

The second acquisition module is configured to acquire, based on the preset image recognition model and the image information, the relative spatial coordinate information of each vertex of the base station antenna based on the location of the drone; the image recognition model is configured to Identify the relative spatial coordinate information of each vertex of the base station antenna contained in the image information;

The calculation module is configured to calculate the pose information of the base station antenna based on the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna.

According to yet another embodiment of the present disclosure, a base station antenna pose information exploration system is also provided, wherein the system includes an image acquisition unit and a data processing unit;

The image collection unit includes a drone; the drone is configured to collect image information of the base station antenna and send the image information to the data processing unit;

The data processing unit is configured to obtain the image information of the base station antenna collected by the drone; according to the preset image recognition model and the image information, obtain the image information of each vertex of the base station antenna based on the location of the drone. Relative spatial coordinate information; the image recognition model is set to identify the relative spatial coordinate information of each vertex of the base station antenna contained in the image information; according to the relative space of the location of the drone and the relative space of each vertex of the base station antenna Coordinate information, calculate the pose information of the base station antenna;

According to yet another embodiment of the present disclosure, a storage medium is also provided, and a computer program is stored in the storage medium, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

According to yet another embodiment of the present disclosure, an electronic device is also provided, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to perform any of the above. Steps in method embodiments.

Description of drawings

The drawings described here are used to provide a further understanding of the present disclosure and constitute a part of the present application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation of the present disclosure. In the attached picture:

Figure 1 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure;

Figure 2 is a system architecture diagram of a base station antenna pose information exploration method provided by an embodiment of the present disclosure;

Figure 3 is a schematic flow chart of a base station antenna pose information exploration method provided by an embodiment of the present disclosure;

Figure 4 is a schematic diagram of relative spatial coordinate information of a base station antenna provided by an embodiment of the present disclosure;

Figure 5 is a schematic diagram for calculating the downtilt angle of a base station antenna provided by an embodiment of the present disclosure;

Figure 6 is a schematic diagram for calculating the azimuth angle of a base station antenna provided by an embodiment of the present disclosure;

Figure 7 is a schematic flow chart of another base station antenna pose information exploration method provided by an embodiment of the present disclosure;

Figure 8 is a schematic structural diagram of a base station antenna pose information exploration device provided by an embodiment of the present disclosure.

Detailed ways

The embodiments of the present disclosure will be described in detail below in conjunction with the embodiments with reference to the accompanying drawings. It should be noted that, as long as there is no conflict, the embodiments and features in the embodiments of this application can be combined with each other.

It should be noted that the terms "first", "second", etc. in the description and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. order.

Example 1

The method embodiment provided in Embodiment 1 of the present application can be executed in a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, FIG. 1 is a hardware structure block diagram of a mobile terminal of a base station antenna pose information exploration method according to an embodiment of the present disclosure. As shown in FIG. 1 , the mobile terminal 10 may include one or more (only one is shown in FIG. 1 ) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. ) and a memory 104 configured to store data. Optionally, the above-mentioned mobile terminal may also include a transmission device 106 configured to have a communication function and an input and output device 108. Persons of ordinary skill in the art can understand that the structure shown in Figure 1 is only illustrative, and it does not limit the structure of the above-mentioned mobile terminal. For example, the mobile terminal 10 may also include more or fewer components than shown in FIG. 1 , or have a different configuration than that shown in FIG. 1 .

The memory 104 may be configured to store computer programs, such as software programs and modules of application software, such as a computer program corresponding to a base station antenna pose information exploration method in an embodiment of the present disclosure. The processor 102 stores the memory 104 in the memory 104 by running A computer program to perform various functional applications and data processing, that is, to implement the above method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely relative to the processor 102, and these remote memories may be accessed via a network. The network is connected to the mobile terminal 10. Examples of the above-mentioned networks include but are not limited to the Internet, intranets, local area networks, mobile communication networks and combinations thereof.

The transmission device 106 is arranged to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of the mobile terminal 10 . In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC for short), which can be connected to other network devices through a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (Radio Frequency, RF for short) module, which is configured to communicate with the Internet wirelessly.

The embodiment of the present application can run on the system architecture shown in Figure 2. As shown in Figure 2, the network architecture at least includes: an image processing unit 201 and a data processing unit 202, where the image processing unit 201 and the data processing unit 202 establish Communication connection.

Optionally, the above system architecture may also include a human-computer interaction device 203, a data cleaning unit 204, a data post-analysis unit 205 and a data transmission unit 206. Persons of ordinary skill in the art can understand that the system architecture shown in Figure 2 is only illustrative, and it does not limit the structure of the above-mentioned mobile terminal. For example, the system architecture may also include more or fewer components than shown in Figure 2, or have a different configuration than shown in Figure 2.

Among them, the image acquisition unit 201 is mainly configured to acquire images of the device to be tested (the device to be tested in this application scenario is the base station antenna), using UAV equipment, in which the spatial coordinates and angle acquisition capabilities of the UAV are important for calculating the antenna angle. , the accuracy of the direction data content is greatly guaranteed, and the drone comes with many sensors, which can directly measure longitude, latitude position information, and flight altitude information. Other types of acquisition equipment require more auxiliary means and cannot meet the current automated process of measurement.

The human-computer interaction device 203, including smart terminals, has two main functions. On the one hand, it is used to display data information, such as the real-time image display of the acquisition equipment (such as the base station antenna, the base station antenna may also be referred to as the antenna below) during the measurement process. Display of post-measurement analysis data, display of post-analysis data, augmented reality (AR) display, etc., and display of the test process. On the other hand, it supports user process operations and is responsible for the operation input of the entire process. in AR display superimposes relevant business information and resource information on the real scene to provide users with information more efficiently and with a higher experience. For example, when the camera of a smart terminal (such as a mobile phone) faces the community, the real scene will be displayed on the screen and displayed on the antenna or in the community. Related information such as direction angle, downtilt angle, altitude, etc. are displayed next to it. After clicking on the information, you can view details or update related information, so what you see is what you get.

The data processing unit 202 includes an AI (Artificial Intelligence) training model, which is mainly configured to recognize the content of the collected images, perform structured processing on the data contained in the images, and automatically and intelligently identify and store the inspection content. . The AI training model mainly uses data-driven methods to detect 3D targets. The steps of model training are annotation of data sets - data enhancement - model training - model quantification - model deployment. Since the annotation dataset requires at least 150k frames of data to ensure 3D object recognition, a large amount of data collection is required. Through data enhancement, the annotated data can be expanded to enhance the training effect. Model training can use 3D target detection models, such as Objectron, Object3DNet, MobilePose, two-stage model, etc. The image recognition of the system can be divided into two parts, one on the mobile side and one on the server side (that is, the data processing unit 202 can be set on the mobile side and the server side, and of course it can also be set up only on the server side without limitation). Model quantification and deployment are Adapt for mobile terminal and server terminal. When there is new content that needs to be identified, the AI training model needs to be incrementally trained and corresponding business algorithms added to gradually improve the data identification accuracy. Since there are so many antenna models, the shapes of different types of antennas are quite different, and the shapes of antennas of the same type are very similar. It is necessary to label the training sources to maintain diversity and ensure the order of magnitude. On this basis, it is also necessary to perform enhanced learning on the training model. , in this way, the accuracy of model identification is enhanced. It is precisely because the antenna shape similarity is high that it needs to be accurately identified through AI. In addition, for important antenna downtilt angle and direction angle data, after the AI training model completes 3D target detection, it combines the output spatial coordinate information with the unique spatial coordinate calculation capability of the UAV, uses spatial geometry to perform fitting, and calculates the corresponding angle and other information.

The data cleaning unit 204 cleans and organizes AI structured data, and checks abnormal data in the process. There is a lot of data content in the inspection process, and the digital information needs to be matched with entities. The data cleaning unit is also responsible for the matching process.

The data post-analysis unit 205 analyzes the data that has been measured and uploaded to the server, and provides progress information for the entire resource management, abnormal prompts for individual device information, and potential Exploring global issues.

The data transmission unit 206 supports the data flow within each subsystem, including the AI training model that is transmitted to the data processing unit 202 after data collection, the structured data is transmitted to the data post-analysis unit 205, and the human-computer interaction device 203 collects the data from the image. The unit 201 and the data post-analysis unit 205 obtain data and so on.

Of course, the functions of the data cleaning unit 204, the data post-analysis unit 205 and the data transmission unit 206 can also be integrated into the data processing unit 202 without limitation.

In this system architecture, because the image recognition model can identify the image information of the base station antenna collected by the drone, and obtain the relative spatial coordinate information of each vertex of the base station antenna, therefore, when the drone collects the image of the base station antenna, no fixed angle measurement is required. , the pose information of the base station antenna can be calculated based on the relative spatial coordinate information of each vertex of the base station antenna and the location of the drone. Therefore, it can solve the technical problems that require high drone control during the measurement process, and achieve a reduction in The technical effects of improving measurement efficiency and measurement accuracy are the requirements for drone pilots and the weather environment requirements during flight.

In this embodiment, a base station antenna pose information exploration method running on the above-mentioned mobile terminal or network architecture is provided. Figure 3 is a flow chart of a base station antenna pose information exploration method according to an embodiment of the present disclosure, as shown in Fig. As shown in 3, the process includes the following steps:

Step S302, obtain the image information of the base station antenna collected by the drone;

Step S304, according to the preset image recognition model and image information, obtain the relative spatial coordinate information of each vertex of the base station antenna based on the position of the drone when collecting the image information; the image recognition model is set to identify the base station antenna contained in the image information. The relative spatial coordinate information of each vertex;

Step S306: Calculate the pose information of the base station antenna based on the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna.

Through the above steps, since the image recognition model can identify the image information of the base station antenna collected by the drone and obtain the relative spatial coordinate information of each vertex of the base station antenna, therefore, when the drone collects the image of the base station antenna, no fixed angle measurement is required. , according to each vertex of the base station antenna The relative spatial coordinate information and the position of the drone are used to calculate the pose information of the base station antenna. Therefore, it can solve the technical problems that require high drone control and weather environment during the measurement process, and reduce the flight time of the drone. requirements to improve the technical effects of measurement efficiency and measurement accuracy.

It should be noted that the image recognition model can be the AI training model in the above system architecture, and based on the calculated pose information of the base station antenna, the AI training model can continue to be trained to further improve the performance during use. Recognition accuracy of AI training model.

Optionally, the execution subject of the above steps can be the server, specifically the data processing unit 202 in the server, but is not limited to this. For example, when it is determined that the base station antenna that needs to be explored is a model that does not require new learning, execute The subject can be mobile.

Optionally, the execution order of step S302 and step S304 is interchangeable, that is, step S304 can be executed first and then S302.

In one embodiment, the pose information includes position information and attitude information; based on the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna, the pose information of the base station antenna is calculated, including:

Calculate the location information of the base station antenna based on the relative spatial coordinate information of the drone's location and each vertex of the base station antenna;

And, calculate the attitude information of the base station antenna based on the relative spatial coordinate information of each vertex of the base station antenna.

In this embodiment, when calculating the attitude information of the base station antenna, it can be implemented based on the relative spatial coordinate information of each vertex of the base station antenna. When you need to calculate the location information of the base station antenna, such as altitude, longitude and latitude, you need a reference object, that is, the height, longitude and latitude of the drone when collecting photos. Since the drone has many built-in sensors, it can directly measure longitude, latitude position information, flight altitude information, etc. It is simple and convenient to directly read the position information collected by the drone sensor.

Next, how to calculate the attitude information of the base station antenna is explained in detail. Attitude information includes downtilt angle and azimuth angle. The relative spatial coordinate information is the moment when the drone collects image information, and the spatial coordinate information of the base station antenna relative to the drone. That is, the drone is the origin of the coordinates, and the base station antenna is the origin of the coordinates. Relative spatial coordinate information of each vertex of the line. Relative spatial coordinate information includes X-axis coordinates, Y-axis coordinates and Z-axis coordinates.

The base station antenna is generally a rectangular parallelepiped structure. Here, the base station antenna is a rectangular parallelepiped structure as an example. That is, the base station antenna includes six surfaces, four of which are side surfaces and two bottom surfaces, as shown in Figure 4.

Based on the relative spatial coordinate information of each vertex of the base station antenna, the attitude information of the base station antenna is calculated, including:

Calculate the downtilt angle of the base station antenna based on the X-axis coordinates of each vertex of the base station antenna and the Z-axis coordinate of each vertex of the base station antenna;

And, calculate the azimuth angle of the base station antenna based on the X-axis coordinates of each vertex of the base station antenna and the Y-axis coordinate of each vertex of the base station antenna.

Among them, calculating the downtilt angle of the base station antenna includes: determining the intersection line of any two adjacent sides of the base station antenna; determining the two vertices included on any intersection line; based on the X-axis coordinates of the two vertices and the Z of the two vertices. Axis coordinates, calculate the downtilt angle of the base station antenna; the downtilt angle is positively related to the modulus of the difference between the two X-axis coordinates, and the downtilt angle is negatively correlated to the modulus of the difference between the two Z-axis coordinates.

The four sides of the base station antenna include a first side and a second side opposite to the first side; the first side may be the front of the base station antenna, and the azimuth angle is the angle between the front of the base station antenna and the due north direction, The front side of the base station antenna generally has identification information, such as product identification information, and the first side can be determined through the identification information contained in the image information.

Calculating the azimuth angle of the base station antenna includes: determining the intersection line of any two adjacent surfaces among the first side, the second side and the two bottom surfaces of the base station antenna; determining the two vertices included on any intersection line; based on the two The X-axis coordinate of the vertex and the Y-axis coordinate of the two vertices are used to calculate the azimuth angle of the base station antenna; the azimuth angle is positively related to the module of the difference between the two Y-axis coordinates, and the azimuth is negatively related to the module of the difference between the two X-axis coordinates.

Specifically, the algorithm is as follows:

Construct a UAV coordinate system, as shown in Figure 4, with the coordinates of the UAV O (x ₀ , y ₀ , z ₀ ) as the origin, where the Y-axis represents true north (the direction of the Y-axis arrow is true north N).

The relative coordinates of the eight vertices A, B, C, D, E, F, G, and H of the base station are:

A(x ₁ , y ₁ , z ₁ ), B (x ₂ , y ₂ , z ₂ ), C (x ₃ , y ₃ , z ₃ ), D (x ₄ , y ₄ , z ₄ ), E( x ₅ , y ₅ , z ₅ ), F (x ₆ , y ₆ , z ₆ ), G (x ₇ , y ₇ , z ₇ ), H (x ₈ , y ₈ , z ₈ )

Calculate the downtilt angle α of the base station antenna: The downtilt angle is the angle between the antenna and the vertical plane (the vertical plane refers to the plane parallel to the X-axis and Z-axis and perpendicular to the ground). The calculation method converts the angle between the antenna and the vertical plane in three-dimensional space into the angle between the lines in two-dimensional space, as shown in Figure 5. Since the four sides of the antenna are all rectangular, generally the vertical side is longer. When calculating the downtilt angle, you only need to take a certain long side, or in other words, you only need to take the line segment where the four sides intersect. According to the line segment Just calculate the angle between the two vertex coordinates on , and you can get:

Right now, α∈(0,π/2)

For example, the line segments that intersect on the four sides are AE, DH, CG, and BF. They can be calculated according to the two vertices contained in any of the line segments according to the above formula, or the four angles can be calculated separately and the average of the four angles can be calculated. There is no limit on the downtilt angle of the base station antenna.

Calculate the azimuth angle β of the base station antenna: The azimuth angle can be understood as the angle through which the plane in the north direction rotates clockwise to coincide with the plane where the antenna is located, that is, the angle between the first side of the base station antenna and the north direction. Map the side of the base station photographed in three-dimensional space to a two-dimensional plane to calculate the base station azimuth angle. The calculation method converts the angle between the plane where the antenna is located in three-dimensional space and the due north direction into the angle between lines in two-dimensional space. angle, as shown in Figure 6. Since the four sides of the antenna are all rectangular, when calculating the azimuth angle, you only need to take one of the short sides, or, as shown in Figure 4, you only need to take any of the sides AD, BC, FG, and EH. The azimuth angle of the base station antenna can be calculated based on the coordinates of the two vertices included in the edge.

It can be concluded that:

i∈[1, 4], j=4-i+1, or j∈[5, 8], i=8-i+5

Right now, β∈(0,2π)

It should be noted that the above i and j are both integers.

In this embodiment, the antenna pose information is obtained through fitting calculation. Due to the arbitrary angle of AI recognition, the impact of flight requirements and external environmental factors is reduced. When the UAV collects image information, fixed angle measurement is not required. Collecting at any angle can automatically identify the relative spatial coordinate information of each vertex of the collected base station antenna, improving measurement efficiency and accuracy.

It should be noted that the base station antenna can also have other shapes and structures, and the method for calculating the downtilt angle and azimuth angle is the same. Here, the base station antenna is a rectangular parallelepiped structure as an example. This does not mean that only the downtilt angle and azimuth angle of the base station antenna with a rectangular parallelepiped structure can be calculated. Persons in the field should understand that in other shapes and structures, the coordinate information of some of the vertices can also be selected to calculate the base station. Downtilt and azimuth of the antenna.

In one embodiment, after calculating the pose information of the base station antenna based on the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna, the method further includes:

The pose information of the base station antenna is sent to the mobile terminal; when the mobile terminal determines that the collected real-time image includes the base station antenna, the pose information of the base station antenna is displayed in the real-time image of the mobile terminal.

In this embodiment, when the mobile terminal turns on the camera and aims at the base station antenna, the pose information of the base station antenna can be displayed in the real-time screen of the mobile terminal, which can conveniently obtain the pose information data of each mobile terminal. During display, It can be displayed next to the base station antenna in the real-time screen, or next to the base station. If it cannot be displayed, it means that the base station antenna has not yet carried out pose information exploration, and the pose information needs to be measured by a drone.

In one embodiment, after calculating the position information of the base station antenna according to the relative spatial coordinate information of the position of the drone and each vertex of the base station antenna, the method further includes:

Perform data cleaning and reorganization of the base station antenna's pose information to detect and correct data anomalies.

In this embodiment, data cleaning and reorganization is not necessary, but the cleaned and reorganized data can screen out abnormal data, correct abnormal collected data, and improve the accuracy of the test.

In one embodiment, a base station antenna pose information exploration method, as shown in Figure 7, includes:

Step S701, inspection and survey start;

Step S702, image and data collection;

Step S703, AI data identification;

Step S704, data cleaning and reorganization;

Step S705, determine whether the test is completed; if the test is completed, execute step 706; if the test is not completed, execute step 702 again;

Step S706, structured storage; after that, step 707 or step 709 can be executed;

Step S707, the server returns data;

Step S708, data correlation analysis;

Step S709, AR/3D display;

Step S710, the inspection and survey is completed.

In this embodiment, the process after the inspection starts is as follows:

The image acquisition unit is powered on, selects the site to be tested, and uses the controller to control the device to take pictures of the site to be tested. The image information including the base station antenna is stored in the mobile phone or server. All operations in the subsequent process are targeted at this site; in the image acquisition During the process, several of the data can be obtained through drone sensing, including longitude, latitude, altitude, pitch angle, and heading angle.

Transmit image information to the AI sub-unit. The AI sub-unit is deployed on the mobile terminal and the server side respectively. The mobile terminal includes a lightweight AI model, which is suitable for situations without a network. Performance and functionality are sacrificed, while the server side is fully The AI model is suitable for transferring images from the mobile terminal to the server when there is a network. Afterwards, AI recognition is performed on the information to be measured. The AI unit performs 3D target recognition on the transmitted image content and obtains the corresponding antenna and spatial coordinates. For important antenna downtilt and direction angle data, after the AI model completes 3D target detection, it combines the output spatial coordinate information with the gimbal sensor, uses spatial geometry to perform dual coordinate system fitting, and calculates the corresponding angle. degree and other information, where the dual coordinate system refers to the coordinate system of the base station antenna and the coordinate system of the drone. The two coordinate systems are fitted into a spatial coordinate system with the drone as the coordinate origin, which facilitates the calculation of downtilt angle and azimuth angle. .

After the data is output, it is transferred to the data cleaning unit to complete data anomaly detection, correction, and data sorting and correspondence.

Determine whether the testing of all resources has been completed. If it is not completed, continue to collect images of other resources. If it is completed, all the identified and cleaned data will be stored in a structured manner, and all values correspond to the images.

Complete the storage of corresponding relationships and data, persist the data, and display the data, such as test progress and data details.

Data correlation analysis: After the end-side data of resources is persisted on the server, mining and analysis can be performed to evaluate the life cycle of the equipment, predict failures, and provide basic data sources for other autonomous network-related systems.

The data after front-end AI recognition and the analysis data stored on the server can be presented to users in a highly visual way. It can be presented in 3D or AR. The 3D method is to model the measurement data and display the three-dimensional model in the 3D map. The AR method is to overlay the basic information of the data on the real scene of the resources at the corresponding location. The corresponding data can display details and other related information, and can be updated.

After the above steps, a resource patrol test is completed.

In this embodiment, the unique spatial coordinate acquisition ability of the UAV is combined with an AI training model that can identify wireless base station antennas to perform spatial coordinate fitting, which can accurately calculate the antenna angle information that is very important to the wireless coverage field. (downtilt angle, direction angle), which greatly helps improve measurement efficiency and accuracy. The use of non-contact image collection such as drones avoids high-risk operations in the resource data collection process, and greatly reduces the requirements on the external environment. Changes in measurement methods will reduce the cost of learning and using tools, and will also greatly improve the efficiency of the measurement process. Highly visual AR and 3D methods provide a more intuitive display, improving user experience and operating efficiency. Unified management of end-side resources and data accuracy Improvement, this kind of data can provide basic data sources for other systems, which is of great help to network self-intelligence.

Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is Better implementation. Based on this understanding, the technical solutions of the embodiments of the present disclosure can be embodied in the form of software products in essence or those that contribute to related technologies. The computer software products are stored in a storage medium (such as ROM/RAM, disk , optical disk), including several instructions to cause a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present disclosure.

Example 2

This embodiment also provides a base station antenna position and attitude information exploration device. The device is configured to implement the above embodiments and preferred implementations. What has already been explained will not be described again. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

Figure 8 is a schematic structural diagram of a base station antenna pose information exploration device according to an embodiment of the present disclosure. As shown in Figure 8, the device includes:

The first acquisition module 802 is configured to acquire the image information of the base station antenna collected by the drone;

The second acquisition module 804 is configured to acquire the relative spatial coordinate information of each vertex of the base station antenna based on the location of the drone based on the preset image recognition model and the image information; the image recognition model is set To identify the relative spatial coordinate information of each vertex of the base station antenna contained in the image information;

The calculation module 806 is configured to calculate the pose information of the base station antenna based on the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna.

Since the image recognition model in the second acquisition module 804 can identify the image information of the base station antenna collected by the drone and obtain the relative spatial coordinate information of each vertex of the base station antenna, therefore, without When humans and machines collect images of the base station antenna, there is no need for fixed angle measurement. The pose information of the base station antenna can be calculated based on the relative spatial coordinate information of each vertex of the base station antenna and the location of the drone. Therefore, it can solve the problem of measuring the base station antenna during the measurement process. Technical issues with high requirements on drone control and weather environment have achieved the technical effect of reducing drone flight requirements and improving measurement efficiency and accuracy.

It should be noted that each of the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but is not limited to this: the above modules are all located in the same processor; or the above modules can be implemented in any combination. The forms are located in different processors.

Example 3

Embodiments of the present disclosure also provide a storage medium in which a computer program is stored, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

Optionally, in this embodiment, the above-mentioned storage medium may be configured to store a computer program for performing the following steps:

According to the preset image recognition model and the image information, the relative spatial coordinate information of each vertex of the base station antenna is obtained based on the position of the drone when collecting the image information; the image recognition model is set to recognize The relative spatial coordinate information of each vertex of the base station antenna contained in the image information;

Calculate the pose information of the base station antenna based on the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna.

Optionally, in this embodiment, the above storage medium may include but is not limited to: U disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), Various media that can store computer programs, such as removable hard drives, magnetic disks, or optical disks.

Example 4

An embodiment of the present disclosure also provides an electronic device, including a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to perform the above The steps in any method embodiment. The memory 104 in FIG. 1 is taken as an example of a memory in the electronic device.

Optionally, the above-mentioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the above-mentioned processor, and the input-output device is connected to the above-mentioned processor.

Optionally, in this embodiment, the above-mentioned processor may be configured to perform the following steps through a computer program:

Optionally, for specific examples in this embodiment, reference can be made to the examples described in the above-mentioned embodiments and optional implementations, and details will not be described again in this embodiment.

Obviously, those skilled in the art should understand that each module or each step of the above-mentioned embodiments of the present disclosure can be implemented by a general computing device, and they can be concentrated on a single computing device, or distributed among multiple computing devices. on a network, optionally, they may be implemented in program code executable by a computing device, such that they may be stored in a storage device for execution by the computing device, and in some cases, may be implemented in a manner different from that described herein The steps shown or described are performed in sequence, or they are separately made into individual integrated circuit modules, or multiple modules or steps among them are made into a single integrated circuit module. As such, disclosed embodiments are not limited to any specific combination of hardware and software.

The above are only preferred embodiments of the present disclosure and are not intended to limit the present disclosure. For those skilled in the art, various modifications and changes may be made to the embodiments of the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the embodiments of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

A base station antenna position and attitude information exploration method, including:

Obtain the image information of the base station antenna collected by the drone;

According to the preset image recognition model and the image information, the relative spatial coordinate information of each vertex of the base station antenna is obtained based on the position of the drone when collecting the image information; the image recognition model is used to identify The relative spatial coordinate information of each vertex of the base station antenna contained in the image information;

Calculate the pose information of the base station antenna based on the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna.
The method according to claim 1, wherein the pose information includes position information and attitude information; according to the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna, the base station antenna is calculated pose information, including:

Calculate the position information of the base station antenna according to the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna;

And, calculate the attitude information of the base station antenna based on the relative spatial coordinate information of each vertex of the base station antenna.
The method according to claim 2, wherein the attitude information includes a downtilt angle and an azimuth angle; the relative spatial coordinate information includes an X-axis coordinate, a Y-axis coordinate and a Z-axis coordinate; according to the relative position of each vertex of the base station antenna, Spatial coordinate information, calculating the attitude information of the base station antenna, including:

Calculate the downtilt angle of the base station antenna according to the X-axis coordinate of each vertex of the base station antenna and the Z-axis coordinate of each vertex of the base station antenna;

And, calculate the azimuth angle of the base station antenna according to the X-axis coordinate of each vertex of the base station antenna and the Y-axis coordinate of each vertex of the base station antenna.
The method of claim 3, wherein the base station antenna includes four sides;

Calculating the downtilt angle of the base station antenna according to the X-axis coordinates of each vertex of the base station antenna and the Z-axis coordinate of each vertex of the base station antenna includes:

Determine the intersection line of any two adjacent sides of the base station antenna;

Determine the two vertices included on any of the intersection lines;

Calculate the downtilt angle of the base station antenna according to the X-axis coordinates of the two vertices and the Z-axis coordinates of the two vertices; the difference between the downtilt angle and the two X-axis coordinates The mode of is positively related, and the downtilt angle is negatively related to the mode of the difference between the two Z-axis coordinates.
The method according to claim 3, wherein the base station antenna includes four sides and two bottom surfaces, and the four sides include a first side and a second side opposite to the first side;

Calculating the azimuth angle of the base station antenna according to the X-axis coordinates of each vertex of the base station antenna and the Y-axis coordinate of each vertex of the base station antenna includes:

Determine the intersection line of any two adjacent surfaces among the first side, the second side and the two bottom surfaces of the base station antenna;

Determine the two vertices included on any of the intersection lines;

Calculate the azimuth angle of the base station antenna according to the X-axis coordinates of the two vertices and the Y-axis coordinates of the two vertices; the difference between the azimuth angle and the two Y-axis coordinates The module is positively related, and the orientation is negatively related to the module of the difference between the two X-axis coordinates.
The method according to claim 1, wherein after calculating the pose information of the base station antenna based on the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna, the method further includes:

Send the posture information of the base station antenna to the mobile terminal; when the mobile terminal determines that the collected real-time picture includes the base station antenna, display the posture of the base station antenna in the real-time picture of the mobile terminal information.
The method according to claim 1, wherein after calculating the pose information of the base station antenna based on the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna, the method further includes:

Perform data cleaning and reorganization on the pose information of the base station antenna to perform data anomaly detection. Test and correct.
A base station antenna position and attitude information exploration device, the device includes:

The first acquisition module is configured to acquire the image information of the base station antenna collected by the drone;

The second acquisition module is configured to acquire, based on the preset image recognition model and the image information, the relative spatial coordinate information of each vertex of the base station antenna based on the location of the drone; the image recognition model is configured to Identify the relative spatial coordinate information of each vertex of the base station antenna contained in the image information;

The calculation module is configured to calculate the pose information of the base station antenna based on the location of the drone and the relative spatial coordinate information of each vertex of the base station antenna.
A base station antenna pose information exploration system, the system includes an image acquisition unit and a data processing unit;

The image collection unit includes a drone; the drone is configured to collect image information of the base station antenna and send the image information to the data processing unit;

The data processing unit is configured to obtain the image information of the base station antenna collected by the drone; according to the preset image recognition model and the image information, obtain the image information of each vertex of the base station antenna based on the location of the drone. Relative spatial coordinate information; the image recognition model is set to identify the relative spatial coordinate information of each vertex of the base station antenna contained in the image information; according to the relative space of the location of the drone and the relative space of each vertex of the base station antenna Coordinate information, calculate the pose information of the base station antenna.
The system according to claim 9, wherein the system further includes a human-computer interaction device and a data cleaning unit;

The human-computer interaction device includes an intelligent terminal. The intelligent terminal is configured to receive the pose information of the base station antenna from the data processing unit. When it is determined that the collected real-time picture includes the base station antenna, in the real-time The pose information of the base station antenna is displayed on the screen;

The data cleaning unit is configured to perform data cleaning and reforming on the pose information of the base station antenna, and use the cleaned and reshaped pose information as the pose information of the base station antenna.
A storage medium in which a computer program is stored, wherein the computer program is configured to execute the method described in any one of claims 1 to 7 when running.
An electronic device includes a memory and a processor, a computer program is stored in the memory, and the processor is configured to run the computer program to perform the method described in any one of claims 1 to 7.