Unmanned aerial vehicle aerial photography flight parameter optimization method, device, equipment and medium

Abstract

The invention relates to an unmanned aerial vehicle aerial photography flight parameter optimization method, device and equipment and a medium, and the method comprises the steps: constructing a multi-target optimization model according to an aerial photography quality evaluation function and an aerial photography efficiency evaluation function, initializing each particle in a particle swarm through employing a preset flight parameter optimization algorithm, according to boundary conditions and target output conditions, the multi-target optimization model is solved to determine a pareto optimal solution set, the boundary conditions comprise flight height constraints and flight speed constraints, and the target output conditions represent the maximum value of an aerial photography quality evaluation function and the minimum value of an aerial photography efficiency evaluation function; the pareto optimal solution set comprises a plurality of optimal flight parameter combinations; and controlling the unmanned aerial vehicle to carry out aerial photography according to the optimal flight parameter combination in the pareto optimal solution set so as to complete flight parameter optimization of aerial photography of the unmanned aerial vehicle. According to the invention, by optimizing the flight parameters and the aerial photography path, the precision and efficiency of image data acquisition can be improved.

Description

Technical Field

[0001] The present application relates to the field of drone control, and in particular to a method for optimizing drone aerial photography flight parameters, a corresponding device, an electronic device, and a computer-readable storage medium. Background Art

[0002] Drone remote sensing, a comprehensive technology that integrates unmanned aerial vehicle (UAV) technology, sensors, remote control, positioning, and communications, enables remote sensing data acquisition, modeling, and analysis. It can accurately extract crop physiological parameters, dynamically assess growth, diagnose nutrition, and monitor growth. It has become a crucial tool in precision agriculture for obtaining temporal and spatial field information on crop conditions and environmental factors. To meet the urgent need for timely, high-resolution, and multi-dimensional agricultural data, the efficient collection of farmland information using drone remote sensing technology has become a quintessential technological paradigm in modern agriculture.

[0003] However, rapidly and accurately acquiring agricultural information relies heavily on high-quality drone remote sensing imagery. The quality of drone-generated images is directly affected by the flight parameters, altitude, and speed. While drones flying at lower altitudes and speeds can produce highly accurate and high-resolution images, this significantly reduces the coverage of individual images. This results in an exponential increase in the number of aerial shots, flight duration, and data processing required to complete the same field mapping and monitoring, leading to a decrease in image acquisition efficiency. Therefore, optimizing drone flight parameters to improve the overall performance of drone aerial photography is crucial.

[0004] At present, the mathematical modeling of aerial photography quality and flight parameters in existing drone flight parameter optimization technologies is relatively simplified, and the specific impact of flight speed on aerial photography quality has not yet been clarified. At the same time, in the construction of aerial photography efficiency objective function, there is no clear direct relationship between flight parameters and aerial photography paths, and the impact of aerial photography overlap rate, aerial photography area shape and camera parameters on aerial photography efficiency has not been fully considered.

[0005] In summary, the applicant has made corresponding explorations in order to solve the above problems. Summary of the Invention

[0006] The purpose of this application is to solve the above problems and provide a method for optimizing the flight parameters of unmanned aerial vehicle aerial photography, a corresponding device, an electronic device and a computer-readable storage medium.

[0007] In order to meet the various objectives of this application, this application adopts the following technical solutions:

[0008] A method for optimizing flight parameters of a UAV aerial photography system, which is proposed to meet one of the purposes of this application, includes:

[0009] Obtaining flight parameters, camera parameters, and image parameters during drone aerial photography, wherein the flight parameters include flight altitude and flight speed; the camera parameters include camera sensor width, camera focal length, exposure time, and the physical size of a single pixel of the camera sensor; and the image parameters include the number of pixels of image width;

[0010] determining a spatial resolution of the aerial image according to the width of the camera sensor, the flight altitude, the camera focal length, and the number of pixels of the image width; determining an image clarity of the aerial image according to the flight speed, the camera focal length, the exposure time, the flight altitude, and the physical size of a single pixel of the camera sensor; and constructing an aerial photography quality evaluation function according to the spatial resolution and the image clarity;

[0011] Calculate and determine the flight path length and turning segment length of the drone in the convex polygon area at the current flight altitude, determine the shortest full coverage path length based on the flight path length and the turning segment length, and construct an aerial photography efficiency evaluation function based on the ratio between the shortest full coverage path length and the flight speed;

[0012] A multi-objective optimization model is constructed according to the aerial photography quality evaluation function and the aerial photography efficiency evaluation function, each particle in the particle population is initialized using a preset flight parameter optimization algorithm, and the multi-objective optimization model is solved according to boundary conditions and target output conditions to determine a Pareto optimal solution set, wherein the boundary conditions include a flight altitude constraint and a flight speed constraint, the target output condition represents a maximum value of the aerial photography quality evaluation function and a minimum value of the aerial photography efficiency evaluation function, and the Pareto optimal solution set includes multiple optimal flight parameter combinations;

[0013] The UAV is controlled to perform aerial photography according to the optimal flight parameter combination in the Pareto optimal solution set, so as to complete the flight parameter optimization of the UAV aerial photography.

[0014] Optionally, the step of determining the spatial resolution of the aerial image according to the width of the camera sensor, the flight altitude, the camera focal length, and the number of pixels of the image width includes:

[0015] Get the width of the camera sensor, the current flight altitude, the camera focal length, and the number of pixels of the image width;

[0016] Calculating and determining a first product between the width of the camera sensor and the current flying height, and calculating and determining a second product between the focal length of the camera and the number of pixels of the image width;

[0017] The spatial resolution of the aerial image at the current flight altitude is determined according to a first ratio between the first product and the second product.

[0018] Optionally, the step of determining the image clarity of the aerial image according to the flight speed, the camera focal length, the exposure time, the flight altitude, and the physical size of a single pixel of the camera sensor includes:

[0019] Get the current flight speed, camera focal length, exposure time, current flight altitude, and the physical size of a single pixel on the camera sensor;

[0020] calculating and determining a third product between the current flight speed, the camera focal length, and the exposure time, and calculating and determining a fourth product between the current flight altitude and the physical size of a single pixel of the camera sensor;

[0021] The image clarity of the aerial image at the current flight altitude and the current flight speed is determined according to a second ratio between the third product and the fourth product.

[0022] Optionally, the step of determining the flight altitude constraint includes:

[0023] Obtaining a camera focal length, a number of pixels of an image width, a width of a camera sensor, a minimum spatial resolution, and a maximum spatial resolution, wherein the flight height constraint represents that the flight height is between a minimum flight height and a maximum flight height;

[0024] calculating a fifth product between the camera focal length and the number of pixels of the image width, calculating a sixth product between the width of the camera sensor and the minimum spatial resolution, and determining the maximum flight altitude based on a third ratio between the fifth product and the sixth product;

[0025] A seventh product between the width of the camera sensor and the maximum spatial resolution is calculated, and the minimum flying height is determined according to a fourth ratio between the fifth product and the seventh product.

[0026] Optionally, the step of determining the flight speed constraint includes:

[0027] Obtain the shooting interval, imaging range length, and heading overlap ratio set for drone aerial photography, where the flight speed constraint indicates that the flight speed is between a minimum flight speed and a maximum flight speed, and the heading overlap ratio indicates the ratio of image overlap between adjacent images along the flight path for each route;

[0028] Calculate and determine a first difference between the value 1 and the heading overlap ratio, and calculate and determine an eighth product between the first difference and the imaging range length;

[0029] The maximum flight speed is determined according to a fifth ratio between the eighth product and the photographing interval.

[0030] Optionally, the steps of constructing a multi-objective optimization model based on the aerial photography quality evaluation function and the aerial photography efficiency evaluation function, initializing each particle in the particle population using a preset flight parameter optimization algorithm, and solving the multi-objective optimization model according to boundary conditions and target output conditions to determine a Pareto optimal solution set include:

[0031] The multi-objective optimization model is used as a fitness function, and a preset flight parameter optimization algorithm is used to randomly generate the position and velocity of each particle in the initial particle swarm. The fitness function value corresponding to each particle is calculated and an initial grid is generated, wherein each particle represents a flight parameter combination constructed by flight velocity and flight altitude;

[0032] Select the global optimal solution gbest to update the position and velocity of the particle swarm, perform a mutation operation, recalculate the fitness function value of each particle to update the individual optimal solution pbest, and determine the non-dominated solution, and filter the non-dominated solution according to the grid density to update the non-dominated solution set rep set;

[0033] Repeat the above steps until the maximum number of iterations is reached or the preset convergence condition is reached, and the iteration ends, and the Pareto optimal solution set is output.

[0034] Optionally, the flight parameter optimization algorithm is a multi-objective particle swarm optimization algorithm; the turning segment length represents the connecting line segment between the starting point and the end point of adjacent routes; and the route length represents the flight distance of the UAV on each route.

[0035] A device for optimizing flight parameters of unmanned aerial photography provided for another purpose of the present application includes:

[0036] a parameter acquisition module configured to acquire flight parameters, camera parameters, and image parameters during the drone aerial photography process, wherein the flight parameters include flight altitude and flight speed; the camera parameters include camera sensor width, camera focal length, exposure time, and the physical size of a single pixel of the camera sensor; and the image parameters include the number of pixels of the image width;

[0037] a quality function construction module configured to determine the spatial resolution of the aerial image based on the width of the camera sensor, the flight altitude, the camera focal length, and the number of pixels of the image width; determine the image clarity of the aerial image based on the flight speed, the camera focal length, the exposure time, the flight altitude, and the physical size of a single pixel of the camera sensor; and construct an aerial photography quality evaluation function based on the spatial resolution and the image clarity;

[0038] an efficiency function construction module configured to calculate and determine a flight path length and a turning segment length of the drone in a convex polygonal area at a current flight altitude, determine a shortest fully covered path length based on the flight path length and the turning segment length, and construct an aerial photography efficiency evaluation function based on a ratio between the shortest fully covered path length and the flight speed;

[0039] a flight parameter optimization module, configured to construct a multi-objective optimization model based on the aerial photography quality evaluation function and the aerial photography efficiency evaluation function, initialize each particle in the particle population using a preset flight parameter optimization algorithm, and solve the multi-objective optimization model according to boundary conditions and target output conditions to determine a Pareto optimal solution set, wherein the boundary conditions include flight altitude constraints and flight speed constraints, the target output conditions represent the maximum value of the aerial photography quality evaluation function and the minimum value of the aerial photography efficiency evaluation function, and the Pareto optimal solution set includes multiple optimal flight parameter combinations;

[0040] The aerial photography control module is configured to control the UAV to perform aerial photography according to the optimal flight parameter combination in the Pareto optimal solution set, so as to complete the flight parameter optimization of the UAV aerial photography.

[0041] An electronic device provided to meet another purpose of the present application includes a central processing unit and a memory, wherein the central processing unit is used to call and run a computer program stored in the memory to execute the steps of the drone aerial photography flight parameter optimization method described in the present application.

[0042] A computer-readable storage medium is provided to meet another purpose of the present application, which stores a computer program implemented according to the UAV aerial photography flight parameter optimization method in the form of computer-readable instructions. When the computer program is called and executed by a computer, the steps included in the corresponding method are executed.

[0043] Compared with the existing technology, the mathematical modeling of aerial photography quality and flight parameters in the existing UAV flight parameter optimization technology in this application is relatively simplified, and the specific impact of flight speed on aerial photography quality has not been clarified. At the same time, in constructing the aerial photography efficiency objective function, the direct relationship between flight parameters and aerial photography paths is not clearly defined. The impact of aerial photography overlap rate, aerial photography area shape, and camera parameters on aerial photography efficiency has not been fully considered. This application includes but is not limited to the following beneficial effects:

[0044] First, this application introduces flight speed as a decision variable for the first time by constructing a new aerial photography quality evaluation function. This measure enables the evaluation function to more comprehensively reflect the quality of aerial images under different UAV flight parameters. The introduction of flight speed helps to more accurately assess the clarity of aerial images, thereby improving the applicability and accuracy of aerial photography quality evaluation. Compared with traditional methods, the aerial photography quality evaluation function of this application can better adapt to different flight environments and flight parameters in actual applications, ensuring that the quality of the collected images better meets the requirements of precision agriculture for high resolution and high timeliness.

[0045] Secondly, the drone flight parameter optimization method proposed in this application takes into account the construction of an aerial photography efficiency evaluation function. By calculating the flight path length and turning section length of the drone in a convex polygonal area at a specific flight altitude, the shortest full coverage path length is obtained, and the aerial photography path is optimized. This enables drones to take aerial photography along the shortest path when completing remote sensing monitoring of large areas of farmland, significantly reducing flight time and data processing volume, and improving data collection efficiency.

[0046] Third, this application introduces a multi-objective optimization model that comprehensively considers the two optimization objectives of aerial photography quality and efficiency. This multi-objective optimization method ensures that flight efficiency is maximized while maintaining aerial image quality. Using a particle swarm optimization algorithm, a Pareto-optimal solution set can be obtained, providing multiple optimal flight parameter combinations and providing a flexible optimization strategy for drone flight.

[0047] Fourthly, the proposed drone flight parameter optimization method is applicable not only to convex polygonal farmland of varying shapes, but also to different types of drones and cameras with varying parameters. This robust adaptability allows the method to be effectively optimized in diverse application scenarios, meeting the needs of remote sensing data collection in a variety of farmland environments.

[0048] Fifth, by combining the optimization goals of aerial photography quality and efficiency, this application can determine the optimal flight parameters and shortest aerial photography paths for drones, reducing ineffective flights and duplicated data collection during the aerial photography process. This advantage is crucial for improving the timeliness and quality of agricultural remote sensing data collection, significantly boosting efficiency in large-scale agricultural monitoring.

[0049] Furthermore, this application can provide a more efficient and higher-quality method for collecting remote sensing data from drones for precision agriculture. By optimizing flight parameters and aerial photography paths, it not only improves the accuracy and efficiency of remote sensing image data acquisition, but also provides reliable technical support for tasks such as dynamic assessment of crop growth, pest and disease monitoring, and nutritional diagnosis, further promoting the development of precision agriculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0051] Figure 1 Schematic diagram of the flow of the method for optimizing flight parameters for drone aerial photography according to an embodiment of the present application;

[0052] Figure 2 A schematic diagram of a process for constructing an aerial photography efficiency objective function in an embodiment of the present application;

[0053] Figure 3 This is a schematic diagram of full coverage path planning for a drone in an embodiment of the present application;

[0054] Figure 4 This is a flowchart of the multi-objective particle swarm optimization algorithm in the embodiment of this application;

[0055] Figure 5 This is a functional block diagram of the UAV aerial photography flight parameter optimization device in an embodiment of the present application;

[0056] Figure 6 Schematic diagram of the structure of the computer device in the embodiment of the present application. DETAILED DESCRIPTION

[0057] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and are not to be construed as limiting the present application.

[0058] It will be understood by those skilled in the art that, unless expressly stated otherwise, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, "connected" or "coupled" as used herein may include wireless connections or wireless couplings. The term "and / or" used herein includes all or any units and all combinations of one or more associated listed items.

[0059] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0060] It will be understood by those skilled in the art that the terms "client," "terminal," and "terminal device" as used herein include both devices that are wireless signal receivers, i.e., devices that only have wireless signal receivers without transmission capabilities, and devices that have receiving and transmitting hardware capable of two-way communication over a two-way communication link. Such devices may include: cellular or other communication devices such as personal computers and tablet computers, which have single-line displays, multi-line displays, or cellular or other communication devices without multi-line displays; PCS (Personal Communications Service), which may combine voice, data processing, fax, and / or data communication capabilities; PDA (Personal Digital Assistant), which may include a radio frequency receiver, a pager, Internet / Intranet access, a web browser, a notepad, a calendar, and / or a GPS (Global Positioning System) receiver; and conventional laptop and / or palmtop computers or other devices, which have and / or include a radio frequency receiver. As used herein, the terms "client," "terminal," or "terminal device" may be portable, transportable, or installed in a vehicle (air, sea, and / or land), or may be adapted and / or configured to operate locally and / or in a distributed manner at any other location on Earth and / or in space. As used herein, the terms "client," "terminal," or "terminal device" may also refer to a communication terminal, an Internet terminal, or a music / video playback terminal, such as a PDA, an MID (Mobile Internet Device), and / or a mobile phone with music / video playback capabilities, or may include a smart TV, a set-top box, or other device.

[0061] The hardware referred to by names such as "server", "client", and "service node" in this application is essentially an electronic device with capabilities equivalent to those of a personal computer. It is a hardware device that has the necessary components revealed by the von Neumann principle, such as a central processing unit (including an arithmetic unit and a controller), a memory, an input device, and an output device. Computer programs are stored in its memory, and the central processing unit loads the program stored in the external memory into the internal memory for execution, executes the instructions in the program, and interacts with the input and output devices to complete specific functions.

[0062] It should be noted that the concept of "server" referred to in this application can also be extended to server clusters. Based on the network deployment principles understood by those skilled in the art, the servers described should be logically divided. In physical space, these servers can be independent of each other but callable through interfaces, or integrated into a single physical computer or a computer cluster. Those skilled in the art should understand this flexibility and should not use it to constrain the implementation of the network deployment method of this application.

[0063] Unless expressly specified, one or more technical features of the present application can be deployed on a server for implementation and accessed by a client through a remote call to obtain an online service interface provided by the server, or can be directly deployed and run on a client for implementation.

[0064] Unless expressly specified otherwise, the neural network models referenced or may be referenced in this application may be deployed on a remote server and remotely called on the client, or may be deployed and directly called on a client with sufficient device capabilities. In some embodiments, when it runs on the client, its corresponding intelligence may be obtained through transfer learning to reduce the requirements for the client's hardware operating resources and avoid excessive occupation of the client's hardware operating resources.

[0065] Unless explicitly specified, the various data involved in this application can be stored remotely on a server or on a local terminal device, as long as they are suitable for being called by the technical solution of this application.

[0066] Those skilled in the art should be aware that although the various methods of this application are described based on the same concept and thus exhibit commonality, unless otherwise specified, these methods can be independently executed. Similarly, the various embodiments disclosed in this application are all based on the same inventive concept. Therefore, concepts with the same expression, as well as concepts that are appropriately transformed for convenience despite different expression, should be understood as equivalent.

[0067] Unless expressly stated to be mutually exclusive, the various embodiments disclosed in this application may be cross-combined with the relevant technical features of the various embodiments to flexibly construct new embodiments, as long as such combination does not deviate from the creative spirit of this application and can meet the needs of the prior art or resolve certain deficiencies in the prior art. Those skilled in the art should be aware of such flexibility.

[0068] See also Figure 1 In one embodiment, the method for optimizing flight parameters of a drone aerial photography system of the present application includes:

[0069] Step S10: Acquire flight parameters, camera parameters, and image parameters during the drone aerial photography process, wherein the flight parameters include flight altitude and flight speed; the camera parameters include camera sensor width, camera focal length, exposure time, and the physical size of a single pixel of the camera sensor; and the image parameters include the number of pixels of the image width;

[0070] The UAV flight parameter optimization system in the terminal device can respond to the UAV aerial photography flight parameter optimization instruction to obtain the flight parameters, camera parameters and image parameters of the UAV aerial photography process, wherein the flight parameters include the flight altitude and flight speed, the camera parameters include the width of the camera sensor, the camera focal length, the exposure time and the physical size of a single pixel of the camera sensor, and the image parameters include the number of pixels of the image width;

[0071] Specifically, flight altitude refers to the vertical height of a drone, or its distance from the ground. Flight altitude affects field of view, image resolution, and shooting angle. Generally, a higher altitude provides a wider field of view, but may reduce image detail.

[0072] Flight speed refers to the horizontal speed of the drone during flight. It affects the stability of aerial photography. Too fast a speed may result in blurry images, while too slow a speed may affect the efficiency of aerial photography. A balance must be struck between image quality and efficiency.

[0073] The width of a camera sensor refers to the physical width of the camera's image sensor. The sensor width directly affects the field of view and image quality. A larger sensor captures more light, thereby improving image quality.

[0074] Camera focal length refers to the focal length of the camera lens, typically measured in millimeters (mm). This determines the lens's field of view. Shorter focal lengths produce a wider image, while longer focal lengths narrow the field of view but allow for more distant detail. Choosing the right focal length is crucial for capturing different scenes.

[0075] Exposure time refers to how long the camera's sensor is exposed to light, usually expressed in seconds or milliseconds. Longer exposure times capture more light but may result in a blurry image. Shorter exposure times produce a sharper image but may make the image too dark, especially in low-light conditions.

[0076] The physical size of a camera sensor's individual pixels refers to the physical size of each pixel on the sensor. Larger pixel sizes allow each pixel to capture more light, improving image quality, especially in low-light conditions. Smaller pixel sizes, on the other hand, can result in increased image noise.

[0077] The number of pixels in the image width refers to the number of pixels in the horizontal direction. The higher the number of pixels, the higher the image resolution and the clearer the details.

[0078] Step S20: determining the spatial resolution of the aerial image based on the width of the camera sensor, the flight altitude, the camera focal length, and the number of pixels of the image width; determining the image clarity of the aerial image based on the flight speed, the camera focal length, the exposure time, the flight altitude, and the physical size of a single pixel of the camera sensor; and constructing an aerial photography quality evaluation function based on the spatial resolution and the image clarity;

[0079] After obtaining the flight parameters, camera parameters, and image parameters of the drone during aerial photography, the spatial resolution of the aerial image is determined based on the width of the camera sensor, the flight altitude, the camera focal length, and the number of pixels of the image width; the image clarity of the aerial image is determined based on the flight speed, the camera focal length, the exposure time, the flight altitude, and the physical size of a single pixel of the camera sensor; and an aerial photography quality evaluation function is constructed based on the spatial resolution and the image clarity;

[0080] In some embodiments, in order to effectively evaluate the quality of aerial photography, spatial resolution (GSD) and sharpness are selected as indicators for evaluating the quality of drone aerial images. The step of determining the spatial resolution of the aerial image based on the width of the camera sensor, the flight altitude, the camera focal length, and the number of pixels of the image width includes:

[0081] Step S201, obtaining the width of the camera sensor, the current flight altitude, the camera focal length, and the number of pixels of the image width;

[0082] Step S202: Calculate and determine a first product between the width of the camera sensor and the current flight altitude, and calculate and determine a second product between the camera focal length and the number of pixels of the image width;

[0083] Step S203: Determine the spatial resolution of the aerial image at the current flight altitude according to a first ratio between the first product and the second product.

[0084] Specifically, the calculation formula of the spatial resolution is expressed as:

[0085]

[0086] Among them, GSD(H) represents the spatial resolution of the aerial image at the current flight altitude of the UAV;

[0087] sensor_width indicates the width of the camera sensor; f indicates the focal length of the camera; H indicates the current flight altitude;

[0088] image_width represents the number of pixels of image width;

[0089] Based on the above calculation formula for spatial resolution, first calculate and determine the first product between the width of the camera sensor sensor_width and the current flight height H, and calculate and determine the second product between the camera focal length f and the number of pixels of the image width image_width; according to the first ratio between the first product and the second product To determine the spatial resolution GSD(H) of the aerial image at the current flight altitude.

[0090] In a further embodiment, the step of determining the image clarity of the aerial image based on the flight speed, the camera focal length, the exposure time, the flight altitude, and the physical size of a single pixel of the camera sensor includes:

[0091] Step S2001: Obtain the current flight speed, camera focal length, exposure time, current flight altitude, and the physical size of a single pixel of the camera sensor;

[0092] Step S2002: calculating and determining a third product of the current flight speed, the camera focal length, and the exposure time, and calculating and determining a fourth product of the current flight altitude and the physical size of a single pixel of the camera sensor;

[0093] Step S2003: Determine the image clarity of the aerial image at the current flight altitude and the current flight speed based on a second ratio between the third product and the fourth product.

[0094] Specifically, the calculation formula of the image clarity is expressed as:

[0095]

[0096] Sharpness(H,V) represents the image clarity of the drone's aerial images at the current flight altitude and speed; V represents the current flight speed; f represents the camera focal length; t represents the camera exposure time, which can be set based on weather type, atmospheric conditions, and flight duration or determined by the camera's automatic exposure; H represents the drone's current flight altitude; and ρ represents the physical size of a single pixel on the camera sensor.

[0097] In some embodiments, to ensure that the evaluation score is positively correlated with the aerial photography quality, the spatial resolution GSD and image clarity Sharpness are taken as the inverse, and the subsequent spatial resolution and image clarity are respectively and express.

[0098] In a further embodiment, the weights of the evaluation indicators (spatial resolution and image clarity) are determined, and an aerial photography quality evaluation function is constructed. The specific calculation steps include:

[0099] Step S100: Determine the objective weight by entropy weight method and randomly generate 100 groups of flight heights H∈[H min , H max ] and flight speed V∈[V min , V max ], where H min Indicates the minimum flight altitude; H max Maximum flight altitude; V min Indicates the minimum flight speed; V max Indicates the maximum flight speed.

[0100] Calculate the spatial resolution corresponding to the flight height H and flight speed V and image clarity According to the 100 sets of flight parameters and the corresponding spatial resolution and clarity values ​​generated, the corresponding information entropy is calculated according to each set of data. The calculation formula of the information entropy is expressed as:

[0101]

[0102] Among them, E j represents information entropy, which is used to measure the uncertainty and information content of each set of data; p ij represents the probability of the i-th group of data under the j-th evaluation index, Y ij represents the value of the jth evaluation index (spatial resolution or image resolution) in the i-th group of data, and the value of n can be 100;

[0103] The weight of each evaluation index is calculated by information entropy calculation. The weight calculation formula of the evaluation index weight is expressed as follows:

[0104]

[0105] Among them, τ i The entropy weight method is used to calculate the objective weight of each evaluation indicator. The entropy weight calculation process is repeated 1000 times. Each time, based on 100 sets of randomly generated flight parameters, the average value of each indicator weight is taken as the final objective weights τ1 and τ2 determined by the entropy weight method. τ1 represents the objective weight of spatial resolution calculated by the entropy weight method; τ2 represents the objective weight of image clarity calculated by the entropy weight method.

[0106] At the same time, record the minimum value of spatial resolution during the calculation of 1000 times and maximum value Minimum image clarity and maximum value To facilitate subsequent normalization.

[0107] Step S200: Determine the subjective weights of spatial resolution and image clarity through AHP, establish a fuzzy judgment matrix by comparing the importance of spatial resolution and image clarity, meet the consistency requirements, and obtain the final subjective weight. and in, represents the subjective weight of spatial resolution calculated by AHP, It represents the subjective weight of image clarity calculated by AHP.

[0108] Step S300, the entropy weight method and the hierarchical method are combined with the combined weighting method to linearly combine the objective weight and the subjective weight. The specific calculation formula is as follows:

[0109]

[0110] Among them, β represents the proportional coefficient of the objective weight in the combined weight; (1-β) represents the proportional coefficient of the subjective weight in the combined weight, and the final combined weights ω1 and ω2 are calculated, among which ω1 represents the combined weight of spatial resolution; ω2 represents the combined weight of image clarity.

[0111] Step S400: Before constructing the aerial photography quality evaluation function, the spatial resolution and image clarity need to be normalized. The normalized spatial resolution and image clarity are calculated using the maximum and minimum normalization method. The normalized calculation formula for spatial resolution is expressed as:

[0112]

[0113] in, represents the spatial resolution before normalization; Indicates the minimum value of spatial resolution; Indicates the maximum value of spatial resolution; represents the normalized spatial resolution.

[0114]

[0115] in, Indicates the image clarity before normalization; Indicates the minimum value of image clarity; Indicates the maximum value of image clarity; Indicates the normalized image clarity.

[0116] Based on the above-determined combined weights of spatial resolution, image clarity, normalized spatial resolution, and normalized image clarity, an aerial photography quality assessment function IQA (Image Quality Assessment) is constructed. The aerial photography quality assessment function IQA is expressed as:

[0117]

[0118] Among them, IQA represents the aerial photography quality evaluation function.

[0119] Step S30: Calculate and determine the flight path length and turning segment length of the drone in the convex polygonal area at the current flight altitude, determine the shortest fully covered path length based on the flight path length and the turning segment length, and construct an aerial photography efficiency evaluation function based on the ratio of the shortest fully covered path length to the flight speed;

[0120] The spatial resolution of the aerial image is determined according to the width of the camera sensor, the flight altitude, the camera focal length, and the number of pixels of the image width. The image clarity of the aerial image is determined according to the flight speed, the camera focal length, the exposure time, the flight altitude, and the physical size of a single pixel of the camera sensor. After constructing an aerial photography quality evaluation function based on the spatial resolution and the image clarity, the route length and the turning section length of the UAV in the convex polygon area at the current flight altitude are calculated and determined. The shortest full coverage path length is determined based on the route length and the turning section length. The aerial photography efficiency evaluation function is constructed based on the ratio between the shortest full coverage path length and the flight speed. The turning section length represents the connecting line segment between the starting point and the end point of adjacent routes. The route length represents the flight distance of the UAV on each route.

[0121] Specifically, see Figure 2, construct the mapping relationship between flight parameters and aerial photography efficiency. The specific steps include:

[0122] Step S1100: Input the vertices of a convex polygonal region, traverse each edge of the polygonal region, calculate the perpendicular distance from each edge of the polygon to the farthest vertex, and select the direction of the edge that minimizes this distance as the optimal flight direction. A convex polygonal region indicates that the boundary of the flight region is composed of multiple vertices, and these vertices are connected to form a "convex" shape, that is, all internal angles are less than 180 degrees. The perpendicular distance to the farthest vertex represents the perpendicular distance from each edge to the farthest vertex within the region (the vertex away from the edge). The optimal flight direction is determined by selecting the edge that minimizes this perpendicular distance and using the direction of this edge as the flight direction of the drone.

[0123] Step S1200: Calculate the route interval d between two adjacent routes of the UAV using the imaging range width α and the lateral overlap rate σ at the current flight altitude of the UAV. The calculation formula of the route interval d between two adjacent routes of the UAV is expressed as:

[0124] d=α·(1-σ),

[0125] Where d represents the interval between two adjacent flight paths of the UAV; α represents the width of the camera's imaging range at the current flight altitude; and σ represents the lateral overlap ratio, which indicates the ratio of the image overlap between adjacent flight paths in the direction perpendicular to the flight path (lateral direction).

[0126] The calculation formula of the imaging range width α is expressed as:

[0127]

[0128] Where α represents the width of the camera's imaging range at the current flight altitude; sensor_width represents the width of the camera sensor; f represents the camera's focal length; and H represents the current flight altitude.

[0129] According to the optimal flight direction, the convex polygon area is rotated to the horizontal direction according to a certain rotation angle, where the rotation angle is θ, which is determined by the slope of the optimal scanning edge. The calculation formula of the rotation angle θ is expressed as:

[0130]

[0131] Among them, (X1, Y1) and (X2, Y) are the coordinates of the two endpoints of the shortest distance edge of the convex polygon area, and θ represents the rotation angle calculated by the coordinates of these two endpoints so that the optimal scanning edge of the convex polygon area can be aligned to the horizontal direction.

[0132] Furthermore, according to the coordinates of the i-th vertex in the original coordinate system (Xi , Y i ), calculate and determine the vertex coordinates (x i ,y i ), and record the vertical coordinate range [y min ,y max ], where the vertex coordinates of the i-th vertex after rotation (x i ,y i ) is calculated as:

[0133] x i =X i ·cosθ+Y i sinθ,

[0134] y i =-X i sinθ+Y i ·cosθ,

[0135] Among them, x i Represents the horizontal coordinate of the i-th vertex after rotation; y i Indicates the vertical coordinate of the i-th vertex after rotation; X i Indicates the horizontal coordinate of the i-th vertex in the original coordinate system; Y i represents the vertical coordinate of the i-th vertex in the original coordinate system; sinθ represents the sine value of the rotation angle θ; cosθ represents the cosine value of the rotation angle θ; i = 1, 2, ..., n, the vertex coordinates (x i ,y i ), and record the vertical coordinate range [y min ,y max ], where [y min ,y max ] represents the vertical coordinate range of the rotated convex polygon area, and represents the minimum and maximum vertical coordinate values ​​of the convex polygon area.

[0136] Step S1300, please refer to Figure 3 , determine the starting position of the initial route, first determine the starting ordinate of the initial route, where the calculation formula of the starting ordinate of the initial route is expressed as:

[0137]

[0138] Among them, y start It represents the starting ordinate of the initial route, which is set to the minimum ordinate plus one and a half imaging range to ensure that the first route is in the correct position; α represents the width of the camera's imaging range at the current flight altitude.

[0139] The parallel lines are divided into equal distances with the route interval d parallel to the bottom plate of the convex polygon area as the routes of the UAV. The calculation formula of the total number of routes n is expressed as:

[0140]

[0141] Where n represents the total number of routes, that is, the number of parallel routes divided longitudinally, which is calculated based on the vertical coordinate range and route interval of the rotated convex polygon area.

[0142] To avoid redundancy and better capture the boundaries of the fields, the margins between the routes and the edges of the convex polygonal area are set to 0. That is, the starting and ending points of each route are the two intersection points of the current route and the edge of the convex polygonal area, and the turning segment is the line segment connecting the starting and ending points of adjacent routes. The length of each route and the turning segment is calculated to obtain the shortest fully covered path length of the drone. The calculation formula for the shortest fully covered path length of the drone is expressed as:

[0143] L=∑L z +L h ,

[0144] Among them, L z is the length of the turning section between each two routes, L h is the route length of each route.

[0145] Step S1400: Calculate the ratio of the shortest full coverage path length L to the drone's flight speed V to determine the shortest time T for the drone to complete aerial photography at the current flight altitude and current flight speed, and establish a mapping relationship between flight parameters and aerial photography efficiency to construct an aerial photography efficiency evaluation function. The aerial photography efficiency evaluation function is expressed as:

[0146]

[0147] Where L(H) represents the shortest full coverage path length at the current flight altitude; V represents the current flight altitude; and T(H, V) represents the shortest time to complete aerial photography at the current flight altitude and current flight speed.

[0148] Step S40: constructing a multi-objective optimization model based on the aerial photography quality evaluation function and the aerial photography efficiency evaluation function, initializing each particle in the particle population using a preset flight parameter optimization algorithm, and solving the multi-objective optimization model according to boundary conditions and target output conditions to determine a Pareto optimal solution set, wherein the boundary conditions include a flight altitude constraint and a flight speed constraint, the target output condition represents the maximum value of the aerial photography quality evaluation function and the minimum value of the aerial photography efficiency evaluation function, and the Pareto optimal solution set includes multiple optimal flight parameter combinations;

[0149] Calculate and determine the flight path length and turning section length of the drone in the convex polygon area at the current flight altitude, determine the shortest full coverage path length based on the flight path length and the turning section length, and construct an aerial photography efficiency evaluation function based on the ratio between the shortest full coverage path length and the flight speed. And the aerial photography efficiency evaluation function A multi-objective optimization model is constructed, each particle in the particle swarm is initialized using a preset flight parameter optimization algorithm, and the multi-objective optimization model is solved according to boundary conditions and target output conditions to determine a Pareto optimal solution set, wherein the boundary conditions include flight altitude constraints and flight speed constraints, the target output conditions represent the maximum value of the aerial photography quality evaluation function and the minimum value of the aerial photography efficiency evaluation function, and the Pareto optimal solution set includes multiple optimal flight parameter combinations; the flight parameter optimization algorithm is a multi-objective particle swarm optimization algorithm;

[0150] In some embodiments, the step of determining a flight altitude constraint includes:

[0151] Step S401, obtaining the camera focal length, the number of pixels of the image width, the width of the camera sensor, the minimum spatial resolution, and the maximum spatial resolution, wherein the flight height constraint represents that the flight height is between the minimum flight height and the maximum flight height;

[0152] Step S402: Calculate and determine a fifth product between the camera focal length and the number of pixels of the image width, calculate and determine a sixth product between the width of the camera sensor and the minimum spatial resolution, and determine the maximum flight altitude based on a third ratio between the fifth product and the sixth product;

[0153] Step S403 : Calculate and determine a seventh product between the width of the camera sensor and the maximum spatial resolution, and determine the minimum flying height according to a fourth ratio between the fifth product and the seventh product.

[0154] Specifically, determine the flight altitude range of the drone, also known as the flight altitude constraint, including:

[0155] According to the spatial resolution requirements of specific aerial photography tasks, GSD min and GSD max To determine the flight altitude range [H min , H max], calculating and determining a fifth product between the camera focal length and the number of pixels of the image width, calculating and determining a sixth product between the width of the camera sensor and the minimum spatial resolution, and determining the maximum flight height based on a third ratio between the fifth product and the sixth product, wherein the calculation formula of the maximum flight height is expressed as:

[0156]

[0157] Among them, H max represents the maximum flight altitude; f represents the focal length of the camera; image_width represents the number of pixels of the image width; sensor_width represents the width of the camera sensor; GSD min Expressed as the minimum spatial resolution.

[0158] A seventh product between the width of the camera sensor and the maximum spatial resolution is calculated and determined, and the minimum flying height is determined according to a fourth ratio between the fifth product and the seventh product, wherein a calculation formula for the minimum flying height is expressed as:

[0159]

[0160] Among them, H min represents the minimum flight altitude; f represents the focal length of the camera; image_width represents the number of pixels of the image width; sensor_width represents the width of the camera sensor; GSD max Indicates the maximum spatial resolution.

[0161] In a further embodiment, the step of determining the flight speed constraint includes:

[0162] Step S4001: Obtain the shooting interval, imaging range length, and heading overlap ratio set for the drone aerial photography, wherein the flight speed constraint indicates that the flight speed is between a minimum flight speed and a maximum flight speed, and the heading overlap ratio indicates the ratio of image overlap between adjacent images along the flight path direction (forward direction) of each route;

[0163] Step S4002: Calculate and determine a first difference between the value 1 and the heading overlap ratio, and calculate and determine an eighth product between the first difference and the imaging range length;

[0164] Step S4003: Determine the maximum flight speed based on a fifth ratio between the eighth product and the photographing interval.

[0165] Specifically, a maximum flight speed constraint is introduced based on the heading overlap rate δ and the photographing interval Δt. The relative displacement of the maximum flight speed within the photographing interval Δt set for the drone aerial photography must satisfy the range constraint of the heading overlap rate δ. A first difference between the value 1 and the heading overlap rate is calculated and determined. The eighth product between the first difference and the length of the imaging range is calculated and determined. The maximum flight speed is determined based on the fifth ratio between the eighth product and the photographing interval time. The calculation formula of the maximum flight speed is expressed as:

[0166]

[0167] 0<V min <V max

[0168] Among them, V min Indicates the minimum flight speed; V max represents the maximum flight speed; l represents the length of the imaging range; Δt represents the interval between photographs.

[0169] The calculation formula of the imaging range length l is expressed as:

[0170]

[0171] Where l represents the imaging range length; sensor_length represents the length of the camera sensor; H represents the current flight altitude; and f represents the camera focal length.

[0172] In a further embodiment, a multi-objective optimization model is constructed based on the aerial photography quality evaluation function and the aerial photography efficiency evaluation function, each particle in the particle population is initialized using a preset flight parameter optimization algorithm, and the multi-objective optimization model is solved according to boundary conditions and target output conditions to determine the Pareto optimal solution set, including the following steps:

[0173] Step S40001: Using the multi-objective optimization model as a fitness function, a preset flight parameter optimization algorithm is used to randomly generate the position and velocity of each particle in the initial particle swarm, and the fitness function value corresponding to each particle is calculated to generate an initial grid, wherein each particle represents a flight parameter combination constructed by flight velocity and flight altitude;

[0174] Step S40002: Select the global optimal solution gbest to update the position and velocity of the particle swarm, perform a mutation operation, recalculate the fitness function value of each particle to update the individual optimal solution pbest, and determine the non-dominated solution. Filter the non-dominated solution according to the grid density to update the non-dominated solution set rep set;

[0175] Step S40003: Repeat the above steps until the maximum number of iterations is reached or the preset convergence condition is reached, and the iteration ends, and the Pareto optimal solution set is output.

[0176] Specifically, if Figure 4 As shown in the figure, the multi-objective particle swarm optimization algorithm is used to optimize the flight parameters, which specifically includes the following steps:

[0177] Step S2100: Use flight parameters as decision variables, set the objective function, determine the dimension nVar and value range [Varmin, Varmax] of the decision variables, define the population size nPop, the maximum number of iterations MaxIt, the non-dominated solution set rep set, the capacity nRep, the number of grid divisions num_Grid, the mutation parameter mu, select the pressure parameter beta, delete the pressure coefficient gamma, the inertia coefficient μ, the attenuation coefficient wdamp, and the learning factors c1 and c2.

[0178] Step S2200: Initialize the population: Randomly generate the particle swarm position x and velocity v within the decision variable range [Varmin, Varmax] as the current particle swarm position and velocity. Calculate the fitness value of each particle as the initial value. By comparing the fitness values ​​of each particle, store all non-dominated solutions in the non-dominated solution set rep. Create an initial grid. Based on the current particle swarm fitness value range, divide each dimension into num_Grid intervals. Record the upper and lower limits of each grid. For each non-dominated solution in the non-dominated solution set rep, determine its index in the grid to which it belongs.

[0179] Step S2300, main loop iteration, which includes:

[0180] Step S23001, select gbest, calculate the particle swarm density N of each grid, and calculate the selection probability P1=e( -beta*N ), the solution in the low-density grid is selected as gbest by roulette.

[0181] Step S23002: Update the speed and position of the particle swarm:

[0182] v i+1 =μ×vi+c1×rand(0,1)×(pbest-xi)+c2×rand(0,1)×(gbest-x i )

[0183] x i+1 =x i +v i+1, the updated position is truncated to one decimal place. For particles whose positions exceed the constraint range, a randomly generated position within the value range [Varmin, Varmax] replaces the original position of the particle to avoid falling into the local optimum and ensure that the particle position is limited within the constraint.

[0184] Step S23003: Calculate the mutation probability it is the current iteration number. The mutation probability changes dynamically with the iteration number. If the random number is less than the mutation probability Pm, a disturbance value is randomly generated. If the mutated solution dominates the original solution, the original solution is replaced; otherwise, it is accepted with a 50% probability.

[0185] Step S23004: Calculate the fitness value of the updated particle, update gbest and pbest, store the current non-dominated solution in the non-dominated solution set rep set, screen the non-dominated solution again in the non-dominated solution set rep set, re-divide the grid based on the non-dominated value range in the current non-dominated solution set rep set, and assign indexes.

[0186] Step S23005: If the number of non-dominated solutions in the non-dominated solution set rep exceeds the maximum capacity nRep, the density of each grid is counted as N, and the probability P2=e is generated according to the density. gamma*N , a non-dominated solution is randomly deleted by selecting a high-density grid using roulette wheel until the maximum capacity nRep requirement is met.

[0187] Step S23006: Finally, determine whether the maximum number of iterations MaxIt is reached. If the number of iterations reaches the set maximum value, go to step S23007; otherwise, update the inertia weight w=w*wdamp and return to step S23001.

[0188] Step S23007: Output the Pareto optimal solution set to obtain the optimal flight parameter combination of the UAV, and complete the UAV flight parameter optimization based on aerial photography quality and aerial photography efficiency.

[0189] In some embodiments, nVar represents the dimension of the decision variable. That is, the number of variables in the optimization problem determines the dimension of the position space of the particle; [Varmin, Varmax] represents the value range of the decision variable. This defines the minimum and maximum values ​​of each decision variable, and the position of each dimension of the particle will be limited to this range; nPop is the population size, which represents the number of particles in the particle swarm optimization algorithm and determines the exploration ability of the search space; it represents the current number of iterations; MaxIt represents the maximum number of iterations; nRep represents the capacity of the non-dominated solution set rep set, and the non-dominated solution set rep set is a set for storing non-dominated solutions. This parameter limits the number of non-dominated solutions that can be stored; mu represents the mutation parameter, which is used to control the intensity or probability of the mutation operation; gamma represents the deletion pressure coefficient, which is used to adjust the probability of deleting the solution, and is usually used to control the solution in the non-dominated solution set rep set. , ensuring that it does not exceed the maximum capacity nRep; μ represents the inertia coefficient, which controls the influence of the current velocity of the particle on the next velocity and is often associated with the historical state of the particle. A larger μ value can maintain the continuous motion of the particle, while a smaller value can enable the particle to quickly adapt to the new optimal position; wdamp represents the attenuation coefficient, which is used to attenuate the inertia coefficient μ. Usually, as the number of iterations increases, μ will gradually decrease, thereby prompting the particle to search the solution space more finely; c1 and c2 represent learning factors, which are the weights of the particle when learning the individual optimal solution (pbest) and the global optimal solution (gbest), respectively. These two parameters are used to adjust how the particle moves towards its own optimal solution and the global optimal solution; x i represents the position of particle i, which is a vector of nVar dimensions. i Represents the speed of particle i, which represents the speed of the particle in the decision space. It is also an nVar-dimensional vector that controls the movement of the particle in space. gbest represents the global optimal solution of the particle swarm. The best solution among all particles is the optimal solution of the swarm. pbest represents the individual optimal solution of particle i. It is the position of the optimal solution encountered by particle i during the iteration process. N represents the density of the particle swarm. It represents the concentration of the position of particles in a certain grid, which determines the selection probability and fitness of the particles. P1 and P2 represent the selection probabilities, where P1 is the probability of selecting particles based on low-density grids, and P2 is the probability of selecting and deleting solutions based on grid density. They select particles or solutions through the roulette wheel algorithm. The rep set represents the non-dominated solution set, which stores all non-dominated solutions in the current iteration (that is, those that are not dominated by other solutions). w represents the inertia weight, which is used to control the speed adjustment of the particle swarm. It is large at the beginning and gradually decreases with the number of iterations.

[0190] Step S50: Control the UAV to perform aerial photography according to the optimal flight parameter combination in the Pareto optimal solution set, so as to complete the flight parameter optimization of the UAV aerial photography.

[0191] A multi-objective optimization model is constructed based on the aerial photography quality evaluation function and the aerial photography efficiency evaluation function, and each particle in the particle population is initialized using a preset flight parameter optimization algorithm. After solving the multi-objective optimization model according to boundary conditions and target output conditions to determine the Pareto optimal solution set, the drone is controlled to perform aerial photography according to the optimal flight parameter combination in the Pareto optimal solution set to complete the flight parameter optimization of the drone aerial photography, wherein the optimal flight parameter combination is constructed by the flight altitude and the flight speed.

[0192] As can be seen from the above embodiments, compared with the prior art, the mathematical modeling of aerial photography quality and flight parameters in the existing UAV flight parameter optimization technology in this application is relatively simplified, and the specific impact of flight speed on aerial photography quality has not yet been clarified. At the same time, in constructing the aerial photography efficiency objective function, the direct relationship between flight parameters and aerial photography paths is not clearly defined, and the impact of aerial photography overlap rate, aerial photography area shape, and camera parameters on aerial photography efficiency has not been fully considered. This application includes but is not limited to the following beneficial effects:

[0193] First, this application introduces flight speed as a decision variable for the first time by constructing a new aerial photography quality evaluation function. This measure enables the evaluation function to more comprehensively reflect the quality of aerial images under different UAV flight parameters. The introduction of flight speed helps to more accurately assess the clarity of aerial images, thereby improving the applicability and accuracy of aerial photography quality evaluation. Compared with traditional methods, the aerial photography quality evaluation function of this application can better adapt to different flight environments and flight parameters in actual applications, ensuring that the quality of the collected images better meets the requirements of precision agriculture for high resolution and high timeliness.

[0194] Secondly, the drone flight parameter optimization method proposed in this application takes into account the construction of an aerial photography efficiency evaluation function. By calculating the flight path length and turning section length of the drone in a convex polygonal area at a specific flight altitude, the shortest full coverage path length is obtained, and the aerial photography path is optimized. This enables drones to take aerial photography along the shortest path when completing remote sensing monitoring of large areas of farmland, significantly reducing flight time and data processing volume, and improving data collection efficiency.

[0195] Third, this application introduces a multi-objective optimization model that comprehensively considers the two optimization objectives of aerial photography quality and efficiency. This multi-objective optimization method ensures that flight efficiency is maximized while maintaining aerial image quality. Using a particle swarm optimization algorithm, a Pareto-optimal solution set can be obtained, providing multiple optimal flight parameter combinations and providing a flexible optimization strategy for drone flight.

[0196] Fourthly, the proposed drone flight parameter optimization method is applicable not only to convex polygonal farmland of varying shapes, but also to different types of drones and cameras with varying parameters. This robust adaptability allows the method to be effectively optimized in diverse application scenarios, meeting the needs of remote sensing data collection in a variety of farmland environments.

[0197] Fifth, by combining the optimization goals of aerial photography quality and efficiency, this application can determine the optimal flight parameters and shortest aerial photography paths for drones, reducing ineffective flights and duplicated data collection during the aerial photography process. This advantage is crucial for improving the timeliness and quality of agricultural remote sensing data collection, significantly boosting efficiency in large-scale agricultural monitoring.

[0198] Furthermore, this application can provide a more efficient and higher-quality method for collecting remote sensing data from drones for precision agriculture. By optimizing flight parameters and aerial photography paths, it not only improves the accuracy and efficiency of remote sensing image data acquisition, but also provides reliable technical support for tasks such as dynamic assessment of crop growth, pest and disease monitoring, and nutritional diagnosis, further promoting the development of precision agriculture.

[0199] See also Figure 5A UAV aerial photography flight parameter optimization device is provided to meet one of the purposes of this application, including a parameter acquisition module 1100, a quality function construction module 1200, an efficiency function construction module 1300, a flight parameter optimization module 1400 and an aerial photography control module 1500. Among them, the parameter acquisition module 1100 is configured to obtain the flight parameters, camera parameters and image parameters of the drone during aerial photography, wherein the flight parameters include flight altitude and flight speed, the camera parameters include the width of the camera sensor, the camera focal length, the exposure time and the physical size of a single pixel of the camera sensor, and the image parameters include the number of pixels of the image width; the quality function construction module 1200 is configured to determine the spatial resolution of the aerial image according to the width of the camera sensor, the flight altitude, the camera focal length and the number of pixels of the image width, determine the image clarity of the aerial image according to the flight speed, the camera focal length, the exposure time, the flight altitude and the physical size of a single pixel of the camera sensor, and construct an aerial photography quality evaluation function according to the spatial resolution and the image clarity; the efficiency function construction module 1300 is configured to calculate and determine the route length and the turning section length of the drone in the convex polygon area at the current flight altitude, according to The route length and the turning section length determine the shortest full coverage path length, and the aerial photography efficiency evaluation function is constructed according to the ratio between the shortest full coverage path length and the flight speed; the flight parameter optimization module 1400 is configured to construct a multi-objective optimization model according to the aerial photography quality evaluation function and the aerial photography efficiency evaluation function, initialize each particle in the particle population using a preset flight parameter optimization algorithm, and solve the multi-objective optimization model according to boundary conditions and target output conditions to determine the Pareto optimal solution set, wherein the boundary conditions include flight altitude constraints and flight speed constraints, the target output conditions represent the maximum value of the aerial photography quality evaluation function and the minimum value of the aerial photography efficiency evaluation function, and the Pareto optimal solution set includes multiple optimal flight parameter combinations; the aerial photography control module 1500 is configured to control the UAV to perform aerial photography according to the optimal flight parameter combination in the Pareto optimal solution set to complete the flight parameter optimization of the UAV aerial photography.

[0200] Based on any embodiment of this application, please refer to Figure 6 Another embodiment of the present application further provides an electronic device, which can be implemented by a computer device, such as Figure 6As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. Among them, the computer-readable storage medium of the computer device stores an operating system, a database, and computer-readable instructions, and the database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor may implement a method for optimizing the flight parameters of unmanned aerial vehicles. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor may execute the method for optimizing the flight parameters of unmanned aerial vehicles of the present application. The network interface of the computer device is used to connect and communicate with the terminal. Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0201] In this embodiment, the processor is used to execute Figure 5 The memory stores the program code and various data required to execute the specific functions of each module in the device. The network interface is used to transmit data between user terminals or servers. The memory in this embodiment stores the program code and data required to execute all modules in the drone aerial photography flight parameter optimization device of this application, and the server can call the server's program code and data to execute the functions of all modules.

[0202] The present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the drone aerial photography flight parameter optimization method described in any embodiment of the present application.

[0203] The present application also provides a computer program product, including a computer program / instruction, which, when executed by one or more processors, implements the steps of the drone aerial photography flight parameter optimization method described in any embodiment of the present application.

[0204] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments of the present application can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of the method. The aforementioned storage medium can be a computer-readable storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0205] The above description is only part of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for optimizing flight parameters of unmanned aerial vehicle (UAV) aerial photography, characterized in that: include: Obtaining flight parameters, camera parameters, and image parameters during drone aerial photography, wherein the flight parameters include flight altitude and flight speed; the camera parameters include camera sensor width, camera focal length, exposure time, and the physical size of a single pixel of the camera sensor; and the image parameters include the number of pixels of image width; determining a spatial resolution of the aerial image according to the width of the camera sensor, the flight altitude, the camera focal length, and the number of pixels of the image width; determining an image clarity of the aerial image according to the flight speed, the camera focal length, the exposure time, the flight altitude, and the physical size of a single pixel of the camera sensor; and constructing an aerial photography quality evaluation function according to the spatial resolution and the image clarity; Calculate and determine the flight path length and turning segment length of the drone in the convex polygon area at the current flight altitude, determine the shortest full coverage path length based on the flight path length and the turning segment length, and construct an aerial photography efficiency evaluation function based on the ratio between the shortest full coverage path length and the flight speed; A multi-objective optimization model is constructed according to the aerial photography quality evaluation function and the aerial photography efficiency evaluation function, each particle in the particle population is initialized using a preset flight parameter optimization algorithm, and the multi-objective optimization model is solved according to boundary conditions and target output conditions to determine a Pareto optimal solution set, wherein the boundary conditions include a flight altitude constraint and a flight speed constraint, the target output condition represents a maximum value of the aerial photography quality evaluation function and a minimum value of the aerial photography efficiency evaluation function, and the Pareto optimal solution set includes multiple optimal flight parameter combinations; The UAV is controlled to perform aerial photography according to the optimal flight parameter combination in the Pareto optimal solution set, so as to complete the flight parameter optimization of the UAV aerial photography.

2. The method for optimizing flight parameters of unmanned aerial vehicle (UAV) aerial photography according to claim 1, wherein: The step of determining the spatial resolution of the aerial image according to the width of the camera sensor, the flight altitude, the camera focal length, and the number of pixels of the image width comprises: Get the width of the camera sensor, the current flight altitude, the camera focal length, and the number of pixels of the image width; Calculating and determining a first product between the width of the camera sensor and the current flight altitude, and calculating and determining a second product between the focal length of the camera and the number of pixels of the image width; The spatial resolution of the aerial image at the current flight altitude is determined according to a first ratio between the first product and the second product.

3. The method for optimizing flight parameters of unmanned aerial vehicle (UAV) aerial photography according to claim 1, wherein: The step of determining the image clarity of the aerial image according to the flight speed, the camera focal length, the exposure time, the flight altitude, and the physical size of a single pixel of the camera sensor comprises: Get the current flight speed, camera focal length, exposure time, current flight altitude, and the physical size of a single pixel on the camera sensor; calculating and determining a third product between the current flight speed, the camera focal length, and the exposure time, and calculating and determining a fourth product between the current flight altitude and the physical size of a single pixel of the camera sensor; The image clarity of the aerial image at the current flight altitude and the current flight speed is determined according to a second ratio between the third product and the fourth product.

4. The method for optimizing flight parameters of unmanned aerial vehicle (UAV) aerial photography according to claim 1, wherein: The steps to determine the flight altitude constraint include: Obtaining a camera focal length, a number of pixels of an image width, a width of a camera sensor, a minimum spatial resolution, and a maximum spatial resolution, wherein the flight height constraint represents that the flight height is between a minimum flight height and a maximum flight height; calculating a fifth product between the camera focal length and the number of pixels of the image width, calculating a sixth product between the width of the camera sensor and the minimum spatial resolution, and determining the maximum flight altitude based on a third ratio between the fifth product and the sixth product; A seventh product between the width of the camera sensor and the maximum spatial resolution is calculated, and the minimum flying height is determined according to a fourth ratio between the fifth product and the seventh product.

5. The method for optimizing flight parameters of unmanned aerial vehicle (UAV) aerial photography according to claim 1, wherein: The steps to determine flight speed constraints include: Obtain the shooting interval, imaging range length, and heading overlap ratio set for drone aerial photography, where the flight speed constraint indicates that the flight speed is between a minimum flight speed and a maximum flight speed, and the heading overlap ratio indicates the ratio of image overlap between adjacent images along the flight path for each route; Calculate and determine a first difference between the value 1 and the heading overlap ratio, and calculate and determine an eighth product between the first difference and the imaging range length; The maximum flight speed is determined according to a fifth ratio between the eighth product and the photographing interval.

6. The method for optimizing flight parameters of unmanned aerial vehicle (UAV) aerial photography according to claim 1, wherein: The steps of constructing a multi-objective optimization model according to the aerial photography quality evaluation function and the aerial photography efficiency evaluation function, initializing each particle in the particle population using a preset flight parameter optimization algorithm, and solving the multi-objective optimization model according to boundary conditions and target output conditions to determine the Pareto optimal solution set include: The multi-objective optimization model is used as a fitness function, and a preset flight parameter optimization algorithm is used to randomly generate the position and velocity of each particle in the initial particle swarm. The fitness function value corresponding to each particle is calculated and an initial grid is generated, wherein each particle represents a flight parameter combination constructed by flight velocity and flight altitude; Select the global optimal solution gbest to update the position and velocity of the particle swarm, perform a mutation operation, recalculate the fitness function value of each particle to update the individual optimal solution pbest, and determine the non-dominated solution, and filter the non-dominated solution according to the grid density to update the non-dominated solution set rep set; Repeat the above steps until the maximum number of iterations is reached or the preset convergence condition is reached, and the iteration ends, and the Pareto optimal solution set is output.

7. The method for optimizing flight parameters of unmanned aerial vehicle (UAV) aerial photography according to claims 1 to 6, characterized in that: The flight parameter optimization algorithm is a multi-objective particle swarm optimization algorithm; the turning segment length represents the connecting line segment between the starting point and the end point of adjacent routes; and the route length represents the flight distance of the UAV on each route.

8. A device for optimizing flight parameters of a UAV aerial photography, characterized in that: include: a parameter acquisition module configured to acquire flight parameters, camera parameters, and image parameters during the drone aerial photography process, wherein the flight parameters include flight altitude and flight speed; the camera parameters include camera sensor width, camera focal length, exposure time, and the physical size of a single pixel of the camera sensor; and the image parameters include the number of pixels of the image width; a quality function construction module configured to determine the spatial resolution of the aerial image based on the width of the camera sensor, the flight altitude, the camera focal length, and the number of pixels of the image width; determine the image clarity of the aerial image based on the flight speed, the camera focal length, the exposure time, the flight altitude, and the physical size of a single pixel of the camera sensor; and construct an aerial photography quality evaluation function based on the spatial resolution and the image clarity; an efficiency function construction module configured to calculate and determine a flight path length and a turning segment length of the drone in a convex polygonal area at a current flight altitude, determine a shortest fully covered path length based on the flight path length and the turning segment length, and construct an aerial photography efficiency evaluation function based on a ratio between the shortest fully covered path length and the flight speed; a flight parameter optimization module, configured to construct a multi-objective optimization model based on the aerial photography quality evaluation function and the aerial photography efficiency evaluation function, initialize each particle in the particle population using a preset flight parameter optimization algorithm, and solve the multi-objective optimization model according to boundary conditions and target output conditions to determine a Pareto optimal solution set, wherein the boundary conditions include flight altitude constraints and flight speed constraints, the target output conditions represent the maximum value of the aerial photography quality evaluation function and the minimum value of the aerial photography efficiency evaluation function, and the Pareto optimal solution set includes multiple optimal flight parameter combinations; The aerial photography control module is configured to control the UAV to perform aerial photography according to the optimal flight parameter combination in the Pareto optimal solution set, so as to complete the flight parameter optimization of the UAV aerial photography.

9. An electronic device comprising a central processing unit and a memory, characterized in that: The central processing unit is configured to call and run a computer program stored in the memory to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that It stores a computer program implemented according to the method described in any one of claims 1 to 7 in the form of computer-readable instructions, and when the computer program is called and executed by a computer, the steps included in the corresponding method are executed.

Images