An unmanned aerial vehicle rice painting operation method and device and electronic equipment

Abstract

The application discloses a kind of unmanned plane rice painting operation method, device and electronic equipment, the method includes: according to the flight state of multiple unmanned planes of rice painting operation instruction control, and distribute corresponding target field area;Target field area is according to the interval of pre-established grid processing, respectively the point cloud data and image data of target field area collected by each unmanned plane are obtained;Respectively, point cloud data and image data are normalized, and after being associated with the flight state of each unmanned plane, generate multiple local area maps;Detect the second overlap area between adjacent local area maps, carry out data screening and splicing integration to second overlap area, then obtain global area map in combination with multiple local area maps;Determine the root position of rice variety and plan operation track, and control multiple unmanned planes to cooperatively emit corresponding light to the root position in time-sharing manner.The application can effectively improve the efficiency and precision of rice painting operation.

Description

Technical Field

[0001] This invention relates to the field of agricultural drone control technology, specifically to a method, apparatus, and electronic equipment for drone-based rice painting operations. Background Technology

[0002] Rice art, also known as paddy field painting, primarily involves creating artwork by planting various varieties of rice in paddy fields. Green and purple-leaved rice are planted in the paddy fields. Before planting, a nine-square grid is drawn in the field using a traditional line marker. Coordinates are then determined according to the design, and the outline of the image or text is traced. Finally, purple seedlings are planted. As the rice grows, the pre-planned graphics or text will appear. As a form of leisure and sightseeing agriculture, rice art has sprung up across the country due to its considerable social benefits. Major agricultural provinces in my country are learning and experimenting with "rice paddy art" festivals. Rice art presents a rural lifestyle close to nature, showcasing both the joy of harvest and the modern look of new rural areas. Rice has evolved from simply providing agricultural products to the public to now radiating influence in multiple aspects such as economy, culture, and ecology. Agricultural development has shown a trend towards multi-functionality, and rice is just one example of this change. In the process of industrial upgrading and development, it has even greater growth potential waiting to be further explored.

[0003] The emergence of rice paddy art is a testament to the progress of agricultural technology and the improvement of people's living standards. Creating rice paddy art requires the support of modern information technology. The process involves using technical tools such as drones, theodolites, and special steel measuring tapes to digitally map the target planting area. Then, software is used to create a plan view and a planting grid construction drawing. The construction drawing is used to accurately locate the trend of the pattern lines and determine the planting area of ​​each color block and the amount of different colored rice varieties to be sown.

[0004] In the process of creating rice paddy art, a single drone is typically used to collect data about the paddy field. However, this method struggles to comprehensively cover and acquire information about the target area, resulting in low efficiency and limited tolerance for errors. Furthermore, the incomplete and inaccurate image data collected and processed by a single drone leads to significant positioning deviations during rice planting and low accuracy in path planning, ultimately resulting in low precision in the rice paddy art and impacting construction efficiency. Additionally, the drone's poor stability during rice paddy art creation makes it susceptible to positional shifts due to external airflow, which also affects data collection, planting positioning, and path planning to varying degrees. Summary of the Invention

[0005] To at least partially overcome the technical problems existing in related technologies, the present invention provides a method, apparatus and electronic device for unmanned aerial vehicle (UAV) rice painting.

[0006] In a first aspect, an embodiment of the present invention provides a method for drone-based rice painting, applied to a server, wherein the server is wirelessly connected to a mobile terminal and multiple drones, and the method includes the following steps:

[0007] The flight status of the multiple drones is controlled according to the rice painting operation instructions sent by the mobile terminal, and corresponding target field areas are assigned. There is a first overlapping area between adjacent target field areas. The flight status includes flight altitude, flight distance and flight attitude.

[0008] The target field area is rasterized at preset intervals to obtain point cloud data and image data of the target field area collected by each UAV.

[0009] The point cloud data and image data are standardized respectively, and then associated with the flight status of each UAV to generate multiple local area maps. There is a second overlapping area between adjacent local area maps.

[0010] The second overlapping area between adjacent local area maps is detected, and the data of the second overlapping area is filtered and stitched together. Then, the global area map is obtained by combining the multiple local area maps.

[0011] The rice painting operation instructions are analyzed to determine the root location of the rice variety and the planned operation trajectory, and the multiple drones are controlled to coordinate and emit corresponding light to the root location in a time-sharing manner.

[0012] Furthermore, the step of filtering and splicing the data in the second overlapping region specifically includes:

[0013] All target drones related to the second overlapping region are obtained based on the first overlapping region;

[0014] Calculate the distance information between all grids in the second overlapping region and all target UAVs, and compare the distance values.

[0015] The system iterates through the point cloud data and image data collected by the target drone with the smallest distance and has undergone normalization processing to generate a local map of the target area.

[0016] Furthermore, the step of determining the root location of the rice variety further includes:

[0017] The motion state change information of the UAV is acquired in real time, including velocity change information, acceleration change information, and displacement change information;

[0018] The global region map is updated synchronously based on the motion state change information;

[0019] The global region map is segmented to obtain a binarized image of the rice field;

[0020] The location of the roots of the rice variety is determined based on the binarized image.

[0021] Furthermore, the step of planning the operation trajectory specifically includes:

[0022] The rice painting operation instructions are parsed to obtain the rice painting operation mode information;

[0023] The terrain information of the global area map is extracted, and the rice painting operation mode information and terrain information are input into the pre-trained artificial neural network to output the operation trajectory in the current state.

[0024] Secondly, an embodiment of the present invention provides a drone-based rice painting device, applied to a server, wherein the server is wirelessly connected to a mobile terminal and multiple drones, and the device includes:

[0025] The control module is used to control the flight status of the multiple drones according to the rice painting operation instructions sent by the mobile terminal, and to allocate corresponding target field areas, wherein there is a first overlapping area between adjacent target field areas, and the flight status includes flight altitude, flight distance and flight attitude;

[0026] The acquisition module is used to rasterize the target field area at preset intervals and acquire point cloud data and image data of the target field area collected by each UAV.

[0027] The local area map generation module is used to standardize the point cloud data and image data respectively, and generate multiple local area maps after associating them with the flight status of each UAV. There is a second overlapping area between adjacent local area maps.

[0028] The global region map generation module is used to detect the second overlapping area between adjacent local region maps, filter and stitch the data of the second overlapping area, and then combine it with the multiple local region maps to obtain the global region map.

[0029] The planning and operation module is used to parse the rice painting operation instructions, determine the root position of the rice variety and the planned operation trajectory, and control the multiple drones to coordinate and emit corresponding light to the root position in a time-sharing manner.

[0030] Furthermore, the global area map generation module specifically includes:

[0031] The target drone acquisition module is used to acquire all target drones related to the second overlapping area based on the first overlapping area;

[0032] The distance comparison calculation module is used to calculate the distance information between all grids in the second overlapping area and all target UAVs, and to compare the distance magnitudes.

[0033] The target local area map generation module is used to traverse and obtain the point cloud data and image data collected by the UAV at the closest target and after normalization processing to generate a target local area map.

[0034] Furthermore, the planning operation module further includes:

[0035] The motion state change acquisition module is used to acquire motion state change information of the UAV in real time, including velocity change information, acceleration change information and displacement change information;

[0036] The synchronization update module is used to synchronously update the global area map based on the motion state change information;

[0037] The segmentation module is used to segment the global region map to obtain a binarized image of the rice field.

[0038] The root location determination module is used to determine the root location of the rice variety based on the binarized image.

[0039] Furthermore, the planning operation module specifically includes:

[0040] The parsing module is used to parse the rice painting operation instructions to obtain rice painting operation mode information;

[0041] The operation trajectory output module is used to extract the terrain information of the global area map, input the rice painting operation mode information and terrain information into the pre-trained artificial neural network, and output the operation trajectory in the current state.

[0042] Thirdly, an electronic device provided by an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0043] The technical solutions provided by the embodiments of the present invention have the following beneficial effects:

[0044] This invention first controls the flight status of multiple drones according to rice painting operation instructions and assigns corresponding target field areas, enabling flexible adaptation to different rice painting operation instructions and effective coordination and allocation of field area ranges for multiple drones. Then, the target field area is rasterized, and point cloud data and image data of the target field area are acquired separately. After standardization processing, these data are associated with the flight status of each drone to generate multiple local area maps. By fully utilizing point cloud data and image data, the accuracy of each local area map is improved. Next, a second overlapping area between adjacent local area maps is detected, and the data of the second overlapping area is filtered and stitched together. Combining multiple local area maps yields a global area map, effectively solving the data coverage and overlap problem between local area maps and improving the accuracy of the global area map. Finally, the rice painting operation instructions are parsed to determine the root position of the rice and plan the operation trajectory. Multiple drones are then controlled to collaboratively emit corresponding light rays to the root position at different times. This adapts to different rice painting operation instructions, accurately determines the root position of the rice variety, and effectively and rationally plans the operation trajectory, improving the efficiency of rice painting operations.

[0045] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

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

[0047] Figure 1 This is a schematic diagram illustrating an application scenario of the drone rice painting method provided in this embodiment of the invention.

[0048] Figure 2 This is a flowchart illustrating the method for creating rice paddy art using drones, as provided in an embodiment of the present invention.

[0049] Figure 3 It is applied to Figure 2 A flowchart illustrating the data filtering and integration process.

[0050] Figure 4 It is applied to Figure 2 A flowchart illustrating the process of determining the root location of a rice variety.

[0051] Figure 5 It is applied to Figure 2 A flowchart illustrating the planned operation trajectory.

[0052] Figure 6 This is a functional block diagram of the drone rice painting device provided in an embodiment of the present invention.

[0053] Figure 7 It is applied to Figure 6 Functional block diagram of the global area map generation module.

[0054] Figure 8 It is applied to Figure 6 Functional block diagram of the planning and operation module.

[0055] The attached figures are labeled as follows:

[0056] Control module 100; Acquisition module 200; Local area map generation module 300; Global area map generation module 400; Planning operation module 500; Target UAV acquisition module 401; Distance comparison calculation module 402; Target local area map generation module 403; Motion state change acquisition module 501; Synchronization update module 502; Segmentation module 503; Root position determination module 504; Parsing module 505; Operation trajectory output module 506. Implementation

[0057] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of methods and apparatus consistent with some aspects of this application as detailed in the appended claims.

[0058] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings. Example

[0059] like Figure 1 The diagram illustrates an application scenario of a drone-based rice painting method according to an embodiment of the present invention. In this embodiment, the drone-based rice painting method can be applied to a server, which is wirelessly connected to a mobile terminal and multiple drones via a 4G or 5G network. The mobile terminal can be a smartphone or tablet, and is primarily used to sense and send rice painting operation instructions to the server. The drone includes a frame, a lifting rotor, multiple sensors, and a light emitter. The multiple sensors are used to collect external data in real time and send it to the server, as well as to execute the relevant instructions sent by the server, thereby completing the corresponding rice painting operation.

[0060] like Figure 2 The diagram shown is a flowchart illustrating a method for creating rice paddy art using a drone, as provided in an embodiment of the present invention. The method mainly includes the following steps:

[0061] Step S100: Control the flight status of the multiple drones according to the rice painting operation instructions sent by the mobile terminal, and assign corresponding target field areas.

[0062] During implementation, the mobile terminal first senses the control signals from the worker, converts them into rice painting operation instructions, and sends them to the server. The server then parses these instructions, precisely controls the flight status of the multiple drones, and assigns a corresponding target field area to each drone. This allows for flexible adaptation to different rice painting operation instructions and effective coordination and allocation of field areas for multiple drones.

[0063] The target field area constitutes the entire working field area, and there is a first overlapping area between adjacent target field areas, which can effectively avoid the generation of blind spots.

[0064] It should be noted that the flight status mainly includes flight altitude, flight spacing, and flight attitude. The flight altitude refers to altitude, the flight spacing includes horizontal and vertical spacing, and the flight attitude can be the pitch angle.

[0065] Step S200: The target field area is rasterized at preset intervals to obtain point cloud data and image data of the target field area collected by each UAV.

[0066] During rasterization, the width of the raster aligns with the longitude direction, and the length of the raster aligns with the latitude direction. Furthermore, the grid spacing is the smallest unit that allows the UAV to clearly capture data.

[0067] In this embodiment, the drones collect point cloud data and image data of their respective target field areas and send the point cloud data and image data to the server. Preferably, the drones collect point cloud data of the target field areas using a laser and image data of the target field areas using a camera or webcam. By fully utilizing the point cloud data and image data, the accuracy of the map of each local area is improved. When collecting point cloud data and image data of the target field areas, the drones also acquire rasterized positioning information of the target field areas.

[0068] Step S300: The point cloud data and image data are normalized respectively, and multiple local area maps are generated after being associated with the flight status of each UAV. There is a second overlapping area between adjacent local area maps.

[0069] To improve data processing efficiency, the point cloud data and image data need to be standardized to form structured data. Then, multiple local area maps are generated by associating them with the flight status of each UAV. Since there is a first overlapping area between adjacent target field areas, correspondingly, there is a second overlapping area between adjacent local area maps.

[0070] Furthermore, in this embodiment, point cloud data and image data can be normalized using a spherical coordinate system and then associated with the flight status of each UAV to generate multiple local area maps.

[0071] Step S400: Detect the second overlapping area between adjacent local area maps, filter and stitch the data of the second overlapping area, and then combine the multiple local area maps to obtain the global area map.

[0072] Specifically, such as Figure 3 As shown, the step of filtering and splicing data in the second overlapping region specifically includes:

[0073] Step S401: Obtain all target UAVs related to the second overlapping area based on the first overlapping area.

[0074] It is understood that multiple drones are pre-assigned to the first overlapping area. All target drones related to the second overlapping area are the pre-assigned multiple drones.

[0075] Step S402: Calculate the distance information between all grids in the second overlapping area and all target UAVs, and compare the distance magnitudes.

[0076] Step S403: Iterate through the point cloud data and image data collected by the target UAV with the smallest distance and after normalization processing to generate a local map of the target area.

[0077] In all grids within the second overlapping region, the distance information between each grid and all target UAVs is calculated, and then the distances are compared. By traversing and obtaining the point cloud data and image data collected by the target UAV with the smallest distance and after normalization processing, a local map of the target area is generated based on the point cloud data and image data.

[0078] By detecting the second overlapping area between adjacent local area maps, filtering and stitching the data of the second overlapping area, and then combining multiple local area maps to obtain a global area map, the problem of data coverage and overlap between local area maps can be effectively solved, and the accuracy of the global area map can be improved.

[0079] Step S500: Analyze the rice painting operation instructions, determine the root position of the rice variety and plan the operation trajectory, and control the multiple drones to coordinately emit corresponding light to the root position in a time-sharing manner.

[0080] Specifically, the server further parses the rice painting operation instructions to obtain rice painting information and determine the rice variety and its root location. Then, based on the rice variety and root location, it plans a reasonable operation trajectory. On the other hand, the server also controls multiple drones to collaboratively emit corresponding light rays to the root location in a time-sharing manner according to the operation trajectory, so as to improve the accuracy and efficiency of the rice painting operation.

[0081] In this embodiment, as Figure 4 As shown, the step of determining the root location of a rice variety further includes:

[0082] Step S501: Acquire the motion state change information of the UAV in real time, including velocity change information, acceleration change information and displacement change information.

[0083] Due to the influence of external environmental factors, such as airflow, the drone may experience a certain degree of deviation. To address this, the drone is equipped with speed sensors, acceleration sensors, and displacement sensors to collect and acquire information on changes in the drone's motion state in real time.

[0084] Step S502: Synchronously update the global area map based on the motion state change information.

[0085] After obtaining the motion state change information, the global area map is obtained and updated synchronously using the coordinate transformation relationship of spherical coordinates.

[0086] Step S503: Segment the global region map to obtain a binarized image of the rice field.

[0087] Using the grid as the smallest unit, the global area map is segmented, and after binarization, a binarized image of the rice field is obtained.

[0088] Step S504: Determine the root location of the rice variety based on the binarized image.

[0089] The binarized image is analyzed to obtain the rice variety and its corresponding root location.

[0090] In this embodiment, as Figure 5 As shown, the steps for planning the work trajectory specifically include:

[0091] Step S505: Parse the rice painting operation instruction to obtain rice painting operation mode information.

[0092] The rice painting operation mode information is obtained according to the rice painting operation instruction. The rice painting operation mode includes time-sharing operation, area-sharing operation, individual operation and collaborative operation.

[0093] Step S506: Extract the terrain information of the global area map, input the rice painting operation mode information and terrain information into the pre-trained artificial neural network, and output the operation trajectory in the current state.

[0094] The terrain information of the global area map is extracted, and then the rice painting operation mode information and terrain information are input into a pre-trained artificial neural network to output an operation trajectory that matches the current operation mode information and conforms to the current terrain information.

[0095] By analyzing the rice painting operation instructions, the location of the rice roots and the planned operation trajectory are determined. Multiple drones are controlled to coordinate and emit corresponding light to the root location in a time-sharing manner. This allows the system to adapt to different rice painting operation instructions, accurately determine the root location of rice varieties, and effectively and rationally plan the operation trajectory, thereby improving the efficiency of rice painting operations. Example

[0096] This invention also provides a drone-based rice painting device, such as... Figure 6 As shown, the device may include a control module 100, an acquisition module 200, a local area map generation module 300, a global area map generation module 400, and a planning operation module 500.

[0097] The drone rice painting device is applied to a server, which is wirelessly connected to a mobile terminal and multiple drones.

[0098] In this embodiment, the control module 100 is used to control the flight status of the multiple drones according to the rice painting operation instructions sent by the mobile terminal, and to allocate corresponding target field areas. There is a first overlapping area between adjacent target field areas, and the flight status includes flight altitude, flight distance, and flight attitude.

[0099] The acquisition module 200 is used to rasterize the target field area according to a preset interval, and acquire point cloud data and image data of the target field area collected by each UAV.

[0100] The local area map generation module 300 is used to standardize the point cloud data and image data respectively, and generate multiple local area maps after associating them with the flight status of each UAV. There is a second overlapping area between adjacent local area maps.

[0101] The global region map generation module 400 is used to detect the second overlapping area between adjacent local region maps, filter and stitch the data of the second overlapping area, and then combine the multiple local region maps to obtain the global region map.

[0102] Further reading Figure 7 The global area map generation module 400 may include a target UAV acquisition module 401, a distance comparison calculation module 402, and a target local area map generation module 403.

[0103] Specifically, the target drone acquisition module 401 is used to acquire all target drones related to the second overlapping area based on the first overlapping area.

[0104] The distance comparison calculation module 402 is used to calculate the distance information between all grids in the second overlapping area and all target UAVs, and to compare the distance magnitudes.

[0105] The target local area map generation module 403 is used to traverse and acquire point cloud data and image data collected by the target UAV with the smallest distance and after normalization processing to generate a target local area map.

[0106] The planning and operation module 500 is used to parse the rice painting operation instructions, determine the root position of the rice variety and the planned operation trajectory, and control the multiple drones to coordinate and emit corresponding light to the root position in a time-sharing manner.

[0107] Further reading Figure 8 The planning operation module 500 may include a motion state change acquisition module 501, a synchronization update module 502, a segmentation module 503, and a root position determination module 504.

[0108] The motion state change acquisition module 501 is used to acquire the motion state change information of the UAV in real time. The motion state change information includes velocity change information, acceleration change information, and displacement change information.

[0109] The synchronization update module 502 is used to synchronously update the global area map according to the motion state change information.

[0110] The segmentation module 503 is used to segment the global region map to obtain a binarized image of the rice field.

[0111] The root location determination module 504 is used to determine the root location of the rice variety based on the binarized image.

[0112] See again Figure 8The planning operation module 500 may further include a parsing module 505 and an operation trajectory output module 506.

[0113] The parsing module 505 is used to parse the rice painting operation instruction to obtain rice painting operation mode information.

[0114] The operation trajectory output module 506 is used to extract the terrain information of the global area map, input the rice painting operation mode information and terrain information into the pre-trained artificial neural network, and output the operation trajectory in the current state.

[0115] Regarding the apparatus in the above embodiments, the specific steps for each module to perform operations have been described in detail in the embodiments related to the method, and will not be elaborated further here. Each module of the above-described UAV rice painting device can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module. Example

[0116] This invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. In implementation, the processor executes the computer program to perform the method steps described in the above embodiments.

[0117] In summary, this embodiment of the invention first controls the flight status of multiple drones according to the rice painting operation instructions and assigns corresponding target field areas, which can flexibly adapt to different rice painting operation instructions and effectively coordinate the allocation of field area ranges of multiple drones. Then, the target field area is rasterized, and point cloud data and image data of the target field area are acquired respectively. After normalization processing, they are associated with the flight status of each drone to generate multiple local area maps. By making full use of point cloud data and image data, the accuracy of each local area map is improved. Next, the second overlapping area between adjacent local area maps is detected, and the data of the second overlapping area is filtered and stitched together. Then, the global area map is obtained by combining multiple local area maps, which can effectively solve the data coverage and overlap problem between local area maps and improve the accuracy of the global area map. Finally, the rice painting operation instructions are parsed to determine the root position of rice and plan the operation trajectory. Multiple drones are controlled to coordinate and emit corresponding light to the root position at different times. This can adapt to different rice painting operation instructions, accurately determine the root position of rice varieties, and effectively and rationally plan the operation trajectory, thereby improving the efficiency of rice painting operation.

[0118] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0119] It should be noted that in the description of this application, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means at least two.

[0120] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the function involved, as will be understood by those skilled in the art to which embodiments of this application pertain.

[0121] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) and field-programmable gate arrays (FPGAs) having suitable combinational logic gates, etc.

[0122] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0123] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0124] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0125] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0126] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for creating rice paddy art using drones, applied to a server, wherein the server is wirelessly connected to a mobile terminal and multiple drones, characterized in that, The method includes the following steps: The flight status of the multiple drones is controlled according to the rice painting operation instructions sent by the mobile terminal, and corresponding target field areas are assigned. There is a first overlapping area between adjacent target field areas. The flight status includes flight altitude, flight distance and flight attitude. The target field area is rasterized at preset intervals to obtain point cloud data and image data of the target field area collected by each UAV. The point cloud data and image data are standardized respectively, and then associated with the flight status of each UAV to generate multiple local area maps. There is a second overlapping area between adjacent local area maps. The second overlapping area between adjacent local area maps is detected, and the data of the second overlapping area is filtered and stitched together. Then, the global area map is obtained by combining the multiple local area maps. The rice painting operation instructions are analyzed to determine the root location of the rice variety and the planned operation trajectory, and the multiple drones are controlled to coordinate and emit corresponding light to the root location in a time-sharing manner.

2. The method for unmanned aerial vehicle (UAV) rice painting as described in claim 1, characterized in that, The step of filtering and splicing data in the second overlapping region specifically includes: All target drones related to the second overlapping region are obtained based on the first overlapping region; Calculate the distance information between all grids in the second overlapping region and all target UAVs, and compare the distance magnitudes. The system iterates through the point cloud data and image data collected by the target drone with the smallest distance and has undergone normalization processing to generate a local map of the target area.

3. The method for unmanned aerial vehicle (UAV) rice painting according to claim 1, characterized in that, The step of determining the root location of a rice variety further includes: The motion state change information of the UAV is acquired in real time, including velocity change information, acceleration change information, and displacement change information; The global region map is updated synchronously based on the motion state change information; The global region map is segmented to obtain a binarized image of the rice field; The location of the roots of the rice variety is determined based on the binarized image.

4. The method for unmanned aerial vehicle (UAV) rice painting operation according to claim 1, characterized in that, The steps for planning the operation trajectory specifically include: The rice painting operation instructions are parsed to obtain the rice painting operation mode information; The terrain information of the global area map is extracted, and the rice painting operation mode information and terrain information are input into the pre-trained artificial neural network to output the operation trajectory in the current state.

5. A drone-based rice painting device, applied to a server, wherein the server is wirelessly connected to a mobile terminal and multiple drones, characterized in that, The device includes: The control module is used to control the flight status of the multiple drones according to the rice painting operation instructions sent by the mobile terminal, and to allocate corresponding target field areas, wherein there is a first overlapping area between adjacent target field areas, and the flight status includes flight altitude, flight distance and flight attitude; The acquisition module is used to rasterize the target field area at preset intervals and acquire point cloud data and image data of the target field area collected by each UAV. The local area map generation module is used to standardize the point cloud data and image data respectively, and generate multiple local area maps after associating them with the flight status of each UAV. There is a second overlapping area between adjacent local area maps. The global region map generation module is used to detect the second overlapping area between adjacent local region maps, filter and stitch the data of the second overlapping area, and then combine it with the multiple local region maps to obtain the global region map. The planning and operation module is used to parse the rice painting operation instructions, determine the root position of the rice variety and the planned operation trajectory, and control the multiple drones to coordinate and emit corresponding light to the root position in a time-sharing manner.

6. The unmanned aerial vehicle (UAV) rice painting device according to claim 5, characterized in that, The global region map generation module specifically includes: The target drone acquisition module is used to acquire all target drones related to the second overlapping area based on the first overlapping area; The distance comparison calculation module is used to calculate the distance information between all grids in the second overlapping area and all target UAVs, and to compare the distance magnitudes. The target local area map generation module is used to traverse and obtain the point cloud data and image data collected by the UAV at the closest target and after normalization processing to generate a target local area map.

7. The unmanned aerial vehicle (UAV) rice painting device according to claim 5, characterized in that, The planning operation module further includes: The motion state change acquisition module is used to acquire motion state change information of the UAV in real time, including velocity change information, acceleration change information and displacement change information; The synchronization update module is used to synchronously update the global area map based on the motion state change information; The segmentation module is used to segment the global region map to obtain a binarized image of the rice field. The root location determination module is used to determine the root location of the rice variety based on the binarized image.

8. The unmanned aerial vehicle (UAV) rice painting device according to claim 5, characterized in that, The planning and operation module further includes: The parsing module is used to parse the rice painting operation instructions to obtain rice painting operation mode information; The operation trajectory output module is used to extract the terrain information of the global area map, input the rice painting operation mode information and terrain information into the pre-trained artificial neural network, and output the operation trajectory in the current state.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

Images