Unmanned aerial vehicle path planning method, device, equipment and storage medium

Abstract

The present application relates to remote sensing control technical field, especially unmanned aerial vehicle path planning method, device, equipment and storage medium are provided.The present application obtains initial point cloud image according to the unmanned aerial vehicle path planning request, and determines initial unmanned aerial vehicle path according to initial path point position, collects target point cloud image of each initial path point in initial unmanned aerial vehicle path, finally compares the target point cloud image collected with preset point cloud image, so as to adjust initial unmanned aerial vehicle path, reach the purpose of planning unmanned aerial vehicle path, avoid the technical problem that the traditional unmanned aerial vehicle path planning process in prior art mainly relies on artificial completion on two-dimensional map, is easy to receive interference, improve the efficiency of unmanned aerial vehicle path planning.

Description

Technical Field

[0001] This invention relates to the field of remote sensing control technology, and in particular to a method, apparatus, device, and storage medium for unmanned aerial vehicle (UAV) path planning. Background Technology

[0002] In recent years, due to the cost-effectiveness and flexibility of drones, they have been widely used in military and civilian fields, such as traffic monitoring, maritime rescue, disaster prevention and mitigation, search and rescue, forest fire prevention, and auxiliary communication. Drone applications have been very successful in these fields.

[0003] However, in various applications, path planning for drones is the foundation for mission completion. Traditional path planning mainly relies on manual work on two-dimensional maps, which is highly arbitrary and cannot control the content of the images captured at the shooting point. This is inconvenient for scenarios with high requirements for the content captured.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide a method, apparatus, device, and storage medium for unmanned aerial vehicle (UAV) path planning, which aims to solve the technical problem that the traditional UAV path planning process mainly relies on manual work on a two-dimensional map, making it susceptible to interference.

[0006] To achieve the above objectives, the present invention provides a method for unmanned aerial vehicle (UAV) path planning, the method comprising the following steps:

[0007] Upon receiving a drone path planning request, an initial point cloud image is obtained based on the drone path planning request;

[0008] Determine the initial path point positions in the initial point cloud image, and determine the initial UAV path based on the initial path point positions;

[0009] Based on the target UAV parameters and the initial point cloud image, obtain the target point cloud image corresponding to the initial path point position;

[0010] The initial UAV path is adjusted based on the target point cloud image and the preset point cloud image to obtain the target UAV path.

[0011] Optionally, obtaining the target point cloud image corresponding to the initial path point position based on the target UAV parameters and the initial point cloud image includes:

[0012] Extract drone attitude information, camera basic parameters, and camera view information from the target drone parameters;

[0013] The target point cloud acquisition range is determined based on the target UAV attitude information, the camera basic parameters, and the camera viewpoint information;

[0014] The target point cloud image is determined based on the target point cloud acquisition range, the initial path point, and the initial point cloud image.

[0015] Optionally, determining the target point cloud image based on the target point cloud acquisition range, the initial path points, and the initial point cloud image includes:

[0016] Obtain the coordinates of each pixel in the initial point cloud image;

[0017] The target region point cloud is determined based on the coordinates of each point cloud pixel, the initial path point, and the target point cloud acquisition range.

[0018] The target region point cloud is marked, and the target point cloud image corresponding to the initial path point position is determined based on the marked target region point cloud.

[0019] Optionally, obtaining the coordinates of each point cloud pixel in the initial point cloud image includes:

[0020] Determine the camera intrinsic parameter matrix and camera extrinsic parameter matrix based on the target UAV parameters;

[0021] Obtain the spatial coordinates of each point in the initial point cloud image;

[0022] The coordinates of each point cloud pixel are determined based on the spatial coordinates of each point cloud, the camera intrinsic parameter matrix, and the camera extrinsic parameter matrix.

[0023] Optionally, after obtaining the initial point cloud image based on the UAV path planning request upon receiving the UAV path planning request, the method further includes:

[0024] The main flight path direction is determined based on the UAV path planning request, and the initial point cloud image is adjusted based on the main flight path direction.

[0025] The initial path points and flight path information of the adjusted initial point cloud image are determined based on the preset path generation rules.

[0026] The target UAV path is generated based on the initial waypoint and the flight path information.

[0027] Optionally, adjusting the initial UAV path based on the target point cloud image and a preset point cloud image to obtain the target UAV path includes:

[0028] Point cloud overlap detection is performed between the target point cloud image and the preset point cloud image;

[0029] When the detection result indicates the presence of missing point clouds, the initial path point positions in the initial UAV path are adjusted according to the detection result to obtain the target path point positions.

[0030] Generate the target drone path based on the location of the target path point.

[0031] Optionally, after adjusting the initial UAV path based on the target point cloud image and a preset point cloud image to obtain the target UAV path, the method further includes:

[0032] The target drone's path is sent to the user's terminal for display;

[0033] Upon receiving a user's display feedback instruction based on the target drone's path, a path guidance file in a preset format is generated according to the display feedback instruction and the target drone's path, so that the target drone can follow the path guidance file for flight guidance.

[0034] Furthermore, to achieve the above objectives, the present invention also proposes a UAV path planning device, the UAV path planning device comprising:

[0035] The image acquisition module is used to acquire an initial point cloud image based on the UAV path planning request when a UAV path planning request is received.

[0036] The path determination module is used to determine the position of the initial path point in the initial point cloud image, and to determine the initial UAV path based on the position of the initial path point;

[0037] The point cloud selection module is used to obtain the target point cloud image corresponding to the position of the initial path point based on the target UAV parameters and the initial point cloud image;

[0038] The path planning module is used to adjust the initial UAV path based on the target point cloud image and the preset point cloud image to obtain the target UAV path.

[0039] Furthermore, to achieve the above objectives, the present invention also proposes a drone path planning device, which includes: a memory, a processor, and a drone path planning program stored in the memory and executable on the processor, wherein the drone path planning program is configured to implement the steps of the drone path planning method described above.

[0040] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a UAV path planning program, which, when executed by a processor, implements the steps of the UAV path planning method described above.

[0041] This invention provides a method for drone path planning. The method includes: upon receiving a drone path planning request, acquiring an initial point cloud image based on the request; determining the positions of initial path points in the initial point cloud image and determining an initial drone path based on the initial path point positions; acquiring a target point cloud image corresponding to the initial path point positions based on target drone parameters and the initial point cloud image; and adjusting the initial drone path based on the target point cloud image and a preset point cloud image to obtain the target drone path. Compared with the prior art of manually planning drone flight paths, this invention acquires an initial point cloud image based on the drone path planning request, determines the initial drone path based on the initial path point positions, collects target point cloud images of each initial path point in the initial drone path, and finally compares the collected target point cloud images with the preset point cloud image to adjust the initial drone path, thereby achieving the purpose of planning the drone path. This avoids the technical problem of traditional drone path planning in the prior art, which mainly relies on manual work on a two-dimensional map and is easily affected by interference, thus improving the efficiency of drone path planning. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of the structure of the UAV path planning device in the hardware operating environment involved in the embodiments of the present invention;

[0043] Figure 2 This is a flowchart illustrating the first embodiment of the UAV path planning method of the present invention;

[0044] Figure 3 This is a flowchart illustrating the second embodiment of the UAV path planning method of the present invention;

[0045] Figure 4 This is a flowchart illustrating the third embodiment of the UAV path planning method of the present invention;

[0046] Figure 5 This is a point cloud image schematic diagram of an embodiment of the UAV path planning method of the present invention;

[0047] Figure 6 This is a schematic diagram of a flight path according to an embodiment of the UAV path planning method of the present invention;

[0048] Figure 7 This is a flowchart illustrating the fourth embodiment of the UAV path planning method of the present invention;

[0049] Figure 8 This is a structural block diagram of the first embodiment of the UAV path planning device of the present invention.

[0050] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0051] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0052] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a drone path planning device in the hardware operating environment of an embodiment of the present invention.

[0053] like Figure 1 As shown, the UAV path planning device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0054] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the UAV path planning device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0055] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a UAV path planning program.

[0056] exist Figure 1In the UAV path planning device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the UAV path planning device of the present invention can be set in the UAV path planning device. The UAV path planning device calls the UAV path planning program stored in the memory 1005 through the processor 1001 and executes the UAV path planning method provided in the embodiment of the present invention.

[0057] This invention provides a method for unmanned aerial vehicle (UAV) path planning, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of a drone path planning method according to the present invention.

[0058] In this embodiment, the UAV path planning method includes the following steps:

[0059] Step S10: Upon receiving a UAV path planning request, obtain an initial point cloud image based on the UAV path planning request.

[0060] It should be noted that the execution subject of the method in this embodiment can be a device with data transmission, data acquisition and data processing functions, such as a drone controller. This embodiment does not impose specific limitations on this, and the drone controller will be used as an example in this embodiment and the following embodiments.

[0061] It is worth noting that the drone path planning request can be a control command issued by the user through the drone control device. The drone control device can be a drone controller, a control computer, or a remote control device, etc. This embodiment does not impose specific limitations on this.

[0062] It should be understood that the initial point cloud image refers to the point cloud image in the current environment. The initial point cloud image can be a pre-acquired point cloud image or a point cloud image directly extracted from the database. This embodiment does not impose specific restrictions on this.

[0063] Step S20: Determine the initial path point positions in the initial point cloud image, and determine the initial UAV path based on the initial path point positions.

[0064] It is understood that the initial path point location can be a path point determined according to the path planning instructions input by the user, or it can be a path point automatically generated from the initial point cloud image. This embodiment does not impose specific restrictions on this.

[0065] The initial drone path is obtained by connecting the initial waypoints sequentially. This initial drone path guides the drone's flight path and ensures that the drone does not deviate from its course. However, in actual operation, due to the differences in the tasks that the drone needs to perform, such as accurately collecting image information of a certain area without missing any areas, the requirements for the drone's flight path are high. Flying according to the initial drone path corresponding to the initial waypoints may not meet the requirements. Therefore, it is necessary to subsequently revise the initial drone path.

[0066] Step S30: Obtain the target point cloud image corresponding to the initial path point position based on the target UAV parameters and the initial point cloud image.

[0067] It should be understood that the target drone parameters can include: setting whether to take pictures at the corresponding waypoint, drone orientation, camera attitude, flight speed, and shooting frequency. In order to correct the drone's flight path, point cloud information of the area will be collected for comparison at each initial waypoint, thereby adjusting the waypoint.

[0068] It is understandable that target point cloud images refer to point cloud images of the area near the path points collected by the UAV during its flight operation along the initial UAV path.

[0069] In practical implementation, it is necessary to determine the range or viewing angle when the drone collects the target point cloud image. For example, when the drone arrives at the waypoint, it can collect point cloud information within a range of 200 meters from the camera's x and y coordinates and 300 meters from its z coordinate as the target point cloud image.

[0070] Step S40: Adjust the initial UAV path based on the target point cloud image and the preset point cloud image to obtain the target UAV path.

[0071] It should be noted that the preset point cloud image refers to the point cloud to be captured in advance, or the actual point cloud image collected in advance. By comparing the point cloud image of the area near the path point with the actual point cloud image of that area, it is possible to determine whether there are any omissions in the point cloud, and also to determine whether the position of the path point needs to be adjusted, so as to achieve accurate path planning, meet the user's needs, and improve the efficiency of drone operations.

[0072] This embodiment provides a method for UAV path planning. The method includes: upon receiving a UAV path planning request, acquiring an initial point cloud image based on the request; determining the positions of initial path points in the initial point cloud image and determining an initial UAV path based on the initial path point positions; acquiring a target point cloud image corresponding to the initial path point positions based on target UAV parameters and the initial point cloud image; and adjusting the initial UAV path based on the target point cloud image and a preset point cloud image to obtain the target UAV path. This embodiment acquires an initial point cloud image based on the UAV path planning request, determines the initial UAV path based on the initial path point positions, collects target point cloud images of each initial path point in the initial UAV path, and finally compares the collected target point cloud images with the preset point cloud image to adjust the initial UAV path, thereby achieving the purpose of planning the UAV path. This avoids the technical problem in the traditional UAV path planning process of the prior art, which mainly relies on manual work on a two-dimensional map and is easily affected by interference, thus improving the efficiency of UAV path planning.

[0073] refer to Figure 3 , Figure 3 This is a flowchart illustrating a second embodiment of a drone path planning method according to the present invention.

[0074] Based on the first embodiment described above, in this embodiment, step S30 includes:

[0075] Step S301: Extract the drone attitude information, camera basic parameters, and camera view information from the target drone parameters.

[0076] It should be noted that drone attitude information refers to information such as drone flight attitude, flight speed, and flight altitude; camera basic parameters can include camera focal length, exposure, and internal and external parameters; camera viewpoint information refers to the direction the camera is facing at a certain point in the drone's path. If a panoramic camera is used, viewpoint information does not need to be considered.

[0077] Step S302: Determine the target point cloud acquisition range based on the target UAV attitude information, the camera basic parameters, and the camera viewpoint information.

[0078] It is worth noting that the target point cloud acquisition range refers to the range within which the UAV collects point cloud information at the path points, such as: within 200 meters of the camera's x and y coordinates, and within 300 meters of the camera's z coordinate, etc. This embodiment does not impose specific limitations on this.

[0079] Step S303: Determine the target point cloud image based on the target point cloud acquisition range, the initial path point, and the initial point cloud image.

[0080] It is understandable that target point cloud images refer to point cloud images of the area near the path points collected by the UAV during its flight operation along the initial UAV path.

[0081] Further, step S303 includes:

[0082] Obtain the coordinates of each pixel in the initial point cloud image;

[0083] The target region point cloud is determined based on the coordinates of each point cloud pixel, the initial path point, and the target point cloud acquisition range.

[0084] The target region point cloud is marked, and the target point cloud image corresponding to the initial path point position is determined based on the marked target region point cloud.

[0085] It is worth noting that point cloud pixel coordinates refer to the coordinates of the point cloud within the acquired image. These coordinates can be calculated using the camera imaging model. The formula for obtaining point cloud pixel coordinates is:

[0086]

[0087] Where M1 refers to the intrinsic parameter matrix of the camera, M2 refers to the extrinsic parameter matrix of the camera, and X... W It refers to world coordinates.

[0088] In the specific implementation, when acquiring the target point cloud image corresponding to the path point, the target point cloud can also be marked. The point cloud markers collected within a preset range for each path point are different colors. When viewing, users can view different colors according to the different path points, making it convenient for users to view the scene information corresponding to each path point.

[0089] Furthermore, if there are multiple markings when marking point clouds, different colors can be displayed based on the different path points during the display stage. This embodiment does not impose specific restrictions on this.

[0090] Further, the step of obtaining the coordinates of each point cloud pixel in the initial point cloud image includes:

[0091] Determine the camera intrinsic parameter matrix and camera extrinsic parameter matrix based on the target UAV parameters;

[0092] Obtain the spatial coordinates of each point in the initial point cloud image;

[0093] The coordinates of each point cloud pixel are determined based on the spatial coordinates of each point cloud, the camera intrinsic parameter matrix, and the camera extrinsic parameter matrix.

[0094] It should be noted that point cloud spatial coordinates refer to the coordinates of the point cloud on the acquired image, which are different from point cloud pixel coordinates.

[0095] The formula for obtaining the intrinsic parameter matrix is:

[0096]

[0097] Where A is the intrinsic parameter matrix, f x The length of the focal length along the x-axis is described using pixels, f y Pixels are used to describe the length of the focal length in the y-axis direction, and u0 and v0 are the actual position coordinates of the pixels.

[0098] The formula for obtaining the extrinsic parameter matrix is:

[0099]

[0100] Where B is the extrinsic parameter matrix, R is a column vector representing the orientation of each coordinate axis of the world coordinate system in the camera coordinate system, and T is the representation of the origin of the world coordinate system in the camera coordinate system.

[0101] This embodiment discloses the extraction of drone attitude information, camera basic parameters, and camera viewpoint information from the parameters of a target drone; determining the target point cloud acquisition range based on the target drone attitude information, the camera basic parameters, and the camera viewpoint information; and determining the target point cloud image based on the target point cloud acquisition range, the initial path point, and the initial point cloud image. This embodiment determines the target point cloud image by determining the drone's point cloud acquisition range based on the drone attitude information, camera basic parameters, and camera viewpoint information, and then acquiring corresponding point cloud information at the path point based on the point cloud acquisition range.

[0102] In this embodiment, step S40 includes:

[0103] Step S401: Perform point cloud overlap detection on the target point cloud image and the preset point cloud image.

[0104] It should be noted that the preset point cloud image refers to the point cloud to be captured in advance, or the actual point cloud image collected in advance. By comparing the point cloud image of the area near the path point with the actual point cloud image of that area, it is possible to determine whether there are any missing point clouds, and also to determine whether the position of the path point needs to be adjusted, so as to achieve accurate path planning, meet the user's needs, and improve the efficiency of drone operations.

[0105] It is understandable that overlap detection refers to whether there is an image with a corresponding point cloud position in the point cloud of the path point region and a preset point cloud image.

[0106] Step S402: When the detection result indicates the presence of missing point clouds, adjust the initial path point position in the initial UAV path according to the detection result to obtain the target path point position.

[0107] It is worth noting that if the target point cloud image and the preset point cloud image do not completely overlap, that is, if there are missing point clouds in the acquired target point cloud image, the position of the initial path point in the drone path can be adjusted so that the missing point cloud information can be collected. Secondly, the point cloud acquisition range can also be adjusted by adjusting the drone attitude information, camera basic parameters and camera view information, so as to obtain point cloud information in the area near the path point.

[0108] Step S403: Generate the target UAV path based on the location of the target path point.

[0109] This embodiment discloses a point cloud overlap detection method for the target point cloud image and a preset point cloud image. When the detection result indicates the presence of missing point clouds, the initial path point positions in the initial UAV path are adjusted according to the detection result to obtain the target path point positions. A target UAV path is generated based on the target path point positions. By performing overlap detection on the target point cloud image, it can be determined that the initial UAV path guiding the UAV flight can collect all point cloud images, thereby improving the efficiency of UAV operations.

[0110] refer to Figure 4 , Figure 4 This is a flowchart illustrating a third embodiment of a drone path planning method according to the present invention.

[0111] Based on the second embodiment described above, in this embodiment, after step S10, the method further includes:

[0112] Step S110: Determine the main flight path direction according to the UAV path planning request, and adjust the initial point cloud image according to the main flight path direction.

[0113] It's worth noting that the main flight path refers to the drone's flight direction determined according to the user's needs, such as downwards or upwards. (Refer to...) Figure 5 Adjusting the initial point cloud image according to the main flight path direction can be achieved by rotating the initial point cloud image clockwise or counterclockwise to the main flight path direction. This embodiment does not impose specific restrictions on this.

[0114] Step S120: Determine the initial path points and flight path information of the adjusted initial point cloud image based on the preset path generation rules.

[0115] It is understandable that the preset path generation rule means that the flight path of the UAV can be planned in a zigzag pattern. In this embodiment, the two zigzag paths are equally spaced, and path points are evenly distributed, with the heading turning at the boundary of the point cloud.

[0116] It is easy to understand that the initial waypoint refers to the first waypoint in the point cloud image where the UAV collects point cloud information; the flight path information includes: waypoint spacing, flight path interval, and turning distance, etc., which are not specifically limited in this embodiment.

[0117] Step S130: Generate the target UAV path based on the initial waypoint and the flight path information.

[0118] In practical implementation, after a user issues a drone path planning request, the path can be automatically generated in one go based on the overall shape of the point cloud. The automatic path generation process first determines the main direction of the flight path, then rotates the point cloud to align with the main direction, and then draws a zigzag flight path starting from the top of the point cloud. Adjacent paths on the zigzag path are evenly spaced, and path points are evenly distributed. The flight path turns around at the boundary of the point cloud, thus generating a path like... Figure 6 The zigzag flight path shown.

[0119] refer to Figure 7 , Figure 7 This is a flowchart illustrating the fourth embodiment of a UAV path planning method according to the present invention.

[0120] Based on the third embodiment described above, in this embodiment, after step S40, the method further includes:

[0121] Step S50: Send the target drone path to the user terminal for display.

[0122] It is understandable that the target drone path is sent to the user's terminal for display so that the user can perform drone operations based on the target drone path.

[0123] Step S60: Upon receiving a user's display feedback instruction based on the target drone's path, generate a path guidance file in a preset format according to the display feedback instruction and the target drone's path, so that the target drone can perform flight guidance according to the path guidance file.

[0124] It is understood that the display feedback command is used to control the drone to perform various operations according to the target drone path, such as traffic monitoring, maritime rescue, disaster prevention and mitigation, search and rescue, forest fire prevention, and auxiliary communication. This embodiment does not impose specific limitations on this.

[0125] In this embodiment, upon receiving a display feedback instruction, a path guidance file in kml format is generated from the target drone's path, which is used to control the drone to perform flight guidance based on the path guidance file.

[0126] This embodiment converts the target drone path into a different format and performs drone operations according to the converted path guidance file, ensuring that the generated target drone path can be adapted to different drone models and avoiding incompatibility issues.

[0127] Furthermore, this embodiment of the invention also proposes a storage medium storing a UAV path planning program, which, when executed by a processor, implements the steps of the UAV path planning method described above.

[0128] Since this storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0129] Reference Figure 8 , Figure 8 This is a structural block diagram of the first embodiment of the UAV path planning device of the present invention.

[0130] like Figure 8 As shown, the UAV path planning device proposed in this embodiment of the invention includes:

[0131] The image acquisition module 10 is used to acquire an initial point cloud image based on the UAV path planning request when a UAV path planning request is received.

[0132] The path determination module 20 is used to determine the position of the initial path point in the initial point cloud image and determine the initial UAV path based on the position of the initial path point.

[0133] The point cloud selection module 30 is used to obtain the target point cloud image corresponding to the initial path point position based on the target UAV parameters and the initial point cloud image.

[0134] The path planning module 40 is used to adjust the initial UAV path based on the target point cloud image and the preset point cloud image to obtain the target UAV path.

[0135] This embodiment provides a method for UAV path planning. The method includes: upon receiving a UAV path planning request, acquiring an initial point cloud image based on the request; determining the positions of initial path points in the initial point cloud image and determining an initial UAV path based on the initial path point positions; acquiring a target point cloud image corresponding to the initial path point positions based on target UAV parameters and the initial point cloud image; and adjusting the initial UAV path based on the target point cloud image and a preset point cloud image to obtain the target UAV path. This embodiment acquires an initial point cloud image based on the UAV path planning request, determines the initial UAV path based on the initial path point positions, collects target point cloud images of each initial path point in the initial UAV path, and finally compares the collected target point cloud images with the preset point cloud image to adjust the initial UAV path, thereby achieving the purpose of planning the UAV path. This avoids the technical problem in the traditional UAV path planning process of the prior art, which mainly relies on manual work on a two-dimensional map and is easily affected by interference, thus improving the efficiency of UAV path planning.

[0136] In one embodiment, the point cloud selection module 30 is further configured to extract drone attitude information, camera basic parameters, and camera view information from the target drone parameters; determine the target point cloud acquisition range based on the target drone attitude information, the camera basic parameters, and the camera view information; and determine the target point cloud image based on the target point cloud acquisition range, the initial path point, and the initial point cloud image.

[0137] In one embodiment, the point cloud selection module 30 is further configured to acquire the coordinates of each point cloud pixel in the initial point cloud image; determine the target region point cloud based on the coordinates of each point cloud pixel, the initial path point, and the target point cloud acquisition range; mark the target region point cloud; and determine the target point cloud image corresponding to the position of the initial path point based on the marked target region point cloud.

[0138] In one embodiment, the point cloud selection module 30 is further configured to determine the camera intrinsic parameter matrix and the camera extrinsic parameter matrix based on the target UAV parameters; obtain the spatial coordinates of each point cloud in the initial point cloud image; and determine the coordinates of each point cloud pixel based on the spatial coordinates of each point cloud, the camera intrinsic parameter matrix, and the camera extrinsic parameter matrix.

[0139] In one embodiment, the image acquisition module 10 is further configured to determine the main flight path direction according to the UAV path planning request, and adjust the initial point cloud image according to the main flight path direction; determine the initial path points and flight path information of the adjusted initial point cloud image based on a preset path generation rule; and generate a target UAV path according to the initial path points and the flight path information.

[0140] In one embodiment, the path planning module 40 is further configured to perform point cloud overlap detection on the target point cloud image and the preset point cloud image; when the detection result indicates that there are missing point clouds, adjust the position of the initial path point in the initial UAV path according to the detection result to obtain the position of the target path point; and generate the target UAV path according to the position of the target path point.

[0141] In one embodiment, the path planning module 40 is further configured to send the target drone path to the user terminal for display; upon receiving a display feedback instruction from the user based on the target drone path, it generates a path guidance file in a preset format according to the display feedback instruction and the target drone path, so that the target drone can perform flight guidance according to the path guidance file.

[0142] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0143] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0144] In addition, for technical details not described in detail in this embodiment, please refer to the UAV path planning method provided in any embodiment of the present invention, which will not be repeated here.

[0145] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0146] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0147] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0148] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for unmanned aerial vehicle path planning, characterized in that, The unmanned aerial vehicle path planning method comprises: Upon receiving an unmanned aerial vehicle path planning request, an initial point cloud image is acquired according to the unmanned aerial vehicle path planning request; An initial path point position in the initial point cloud image is determined, and an initial unmanned aerial vehicle path is determined according to the initial path point position; A target point cloud image corresponding to the initial path point position is acquired based on target unmanned aerial vehicle parameters and the initial point cloud image; The initial unmanned aerial vehicle path is adjusted according to the target point cloud image and a preset point cloud image to obtain a target unmanned aerial vehicle path; The initial unmanned aerial vehicle path is adjusted according to the target point cloud image and a preset point cloud image to obtain a target unmanned aerial vehicle path, which comprises: Point cloud overlap detection is performed on the target point cloud image and the preset point cloud image; When the detection result is that there are missing point clouds, the initial path point position in the initial unmanned aerial vehicle path is adjusted according to the detection result to obtain a target path point position; A target unmanned aerial vehicle path is generated according to the target path point position; The target point cloud image corresponding to the initial path point position is acquired based on target unmanned aerial vehicle parameters and the initial point cloud image, which comprises: Unmanned aerial vehicle attitude information, camera basic parameters and camera view angle information in the target unmanned aerial vehicle parameters are extracted; A target point cloud collection range is determined according to the unmanned aerial vehicle attitude information, the camera basic parameters and the camera view angle information; A target point cloud image is determined according to the target point cloud collection range, the initial path point position and the initial point cloud image; The target point cloud image is determined according to the target point cloud collection range, the initial path point position and the initial point cloud image, which comprises: Coordinates of each point cloud pixel point in the initial point cloud image are acquired; A target area point cloud is determined according to the coordinates of each point cloud pixel point, the initial path point position and the target point cloud collection range; The target area point cloud is labeled, and a target point cloud image corresponding to the initial path point position is determined based on the labeled target area point cloud. 2.The UAV path planning method of claim 1, wherein, The coordinates of each point cloud pixel point in the initial point cloud image are acquired, which comprises: Camera intrinsic parameter matrices and camera extrinsic parameter matrices are determined according to the target unmanned aerial vehicle parameters; Each point cloud spatial coordinate in the initial point cloud image is acquired; Each point cloud pixel point coordinate is determined according to the each point cloud spatial coordinate, the camera intrinsic parameter matrices and the camera extrinsic parameter matrices. 3.The method of claim 1, wherein, After the initial point cloud image is acquired according to the unmanned aerial vehicle path planning request upon receiving the unmanned aerial vehicle path planning request, the main air route direction is determined according to the unmanned aerial vehicle path planning request, and the initial point cloud image is adjusted according to the main air route direction; The initial path point and air route information of the adjusted initial point cloud image are determined based on a preset path generation rule; A target unmanned aerial vehicle path is generated according to the initial path point and the air route information. After the target unmanned aerial vehicle path is obtained by adjusting the initial unmanned aerial vehicle path according to the target point cloud image and the preset point cloud image, the target unmanned aerial vehicle path is sent to a user end for display. 4.The method of any one of claims 1-3, wherein, ​ ​ When receiving a display feedback instruction of the user based on the target UAV path, a path guidance file in a preset format is generated according to the display feedback instruction and the target UAV path, so that the target UAV performs flight guidance according to the path guidance file.

5. An unmanned aerial vehicle path planning apparatus, characterized by, The UAV path planning device comprises: An image acquisition module is configured to acquire an initial point cloud image according to the UAV path planning request when receiving the UAV path planning request; A path determination module is configured to determine an initial path point position in the initial point cloud image, and determine an initial UAV path according to the initial path point position; A point cloud selection module is configured to acquire a target point cloud image corresponding to the initial path point position based on target UAV parameters and the initial point cloud image; A path planning module is configured to adjust the initial UAV path according to the target point cloud image and a preset point cloud image, and obtain a target UAV path; The path planning module is further configured to perform point cloud overlap detection on the target point cloud image and the preset point cloud image; when the detection result is that there is missing point cloud, adjust the initial path point position in the initial UAV path according to the detection result to obtain a target path point position; and generate a target UAV path according to the target path point position; The point cloud selection module is further configured to extract UAV attitude information, camera basic parameters and camera view angle information in the target UAV parameters; determine a target point cloud acquisition range according to the UAV attitude information, the camera basic parameters and the camera view angle information; determine a target point cloud image according to the target point cloud acquisition range, the initial path point position and the initial point cloud image, specifically, acquire coordinates of each point cloud pixel point in the initial point cloud image; determine a target area point cloud according to the coordinates of each point cloud pixel point, the initial path point position and the target point cloud acquisition range; label the target area point cloud, and determine a target point cloud image corresponding to the initial path point position based on the labeled target area point cloud. 6.A UAV path planning device, characterized by, The UAV path planning device comprises a memory, a processor and a UAV path planning program stored on the memory and executable on the processor, and the UAV path planning program is configured to implement the UAV path planning method in any one of claims 1 to 4.

7. A storage medium, characterized by The storage medium stores a UAV path planning program, and the UAV path planning program is executed by the processor to implement the UAV path planning method in any one of claims 1 to 4.

Images