A method and system for controlling aerial photography of a shared unmanned aerial vehicle in a public area

Abstract

The present invention provides a public area shared unmanned aerial photography control method and system, which relates to the technical field of unmanned aerial vehicles. The method includes: establishing an unmanned aerial photography sharing platform, including unmanned aerial vehicle scheduling management, flight mission allocation, aerial photography data processing and user authority management functions; encoding the parameter area, height, angle, and time of the initial aerial photography request as genes; initializing a population, wherein each individual in the population represents an aerial photography request combination; defining an evaluation function for evaluating the pros and cons of each aerial photography request combination; and determining the individuals in the population to perform crossover and mutation operations according to the evaluation function until a preset number of iterations is reached to obtain the final aerial photography request. The present invention realizes the optimal scheduling of unmanned aerial vehicle resources, the reasonable allocation of flight missions, the efficient processing of aerial photography data, and the precise management of user authority, and provides users with convenient, safe, and high-quality aerial photography services.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a method and system for controlling aerial photography of unmanned aerial vehicles shared in public areas. Background Art

[0002] In the traditional operation mode, the flight path and safety of drones depend on the operator's personal experience and judgment. This increases the risk of flight accidents, especially in complex public area environments, such as over cities or densely populated areas. Traditional drone aerial photography generates a huge amount of data, but lacks an effective data processing and sharing mechanism. Operators need to spend a lot of time on post-processing of data, and data sharing is usually limited by file format, size and network transmission speed, making timely use of data and collaboration difficult. Without a unified aerial photography management platform, it is difficult for various operating teams to coordinate, resulting in information islands and duplication of work. At the same time, this also makes it difficult for regulators to effectively monitor and manage drone aerial photography activities.

[0003] In the traditional aerial photography process, the management of user rights is unclear, and data security and privacy protection are difficult to guarantee. Different users cannot clearly define their respective access and usage rights, which can easily lead to data leakage or abuse. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a public area shared drone aerial photography control method and system, which realizes efficient and intelligent management of drone aerial photography and improves the processing speed and safety of flight missions.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] In a first aspect, a method for controlling aerial photography of a shared drone in a public area is provided, the method comprising:

[0007] Establish a drone aerial photography sharing platform, including drone dispatch management, flight mission allocation, aerial photography data processing and user authority management functions;

[0008] Encode the parameters of the initial aerial photography request, such as area, height, angle, and time, into genes; initialize a population, where each individual in the population represents an aerial photography request combination; define an evaluation function for evaluating the quality of each aerial photography request combination based on the importance of the aerial photography area, the impact of the height and angle on the shooting effect, and the suitability of the time window; determine the individuals in the population to perform crossover and mutation operations based on the evaluation function until the preset number of iterations is reached to obtain the final aerial photography request;

[0009] The sharing platform receives the final aerial photography request and verifies it. After verification, it extracts key information from the final aerial photography request and determines the final drone that will perform the task. If there are multiple aerial photography requests pointing to the same area at the same time, the sharing platform detects and resolves the conflict, allowing the task to continue to be executed to obtain the processing result.

[0010] According to the processing results, the flight route is automatically determined, and aerial photography operations are performed, and the aerial photography data is transmitted to the sharing platform in real time;

[0011] The sharing platform performs color correction, noise removal, and image enhancement operations on the aerial photography data, and sends the processed aerial photography data to the user authority management center.

[0012] Furthermore, the sharing platform receives the final aerial photography request and verifies the final aerial photography request. After verification, the platform extracts key information from the final aerial photography request and determines the final drone to perform the mission, including:

[0013] Set up a listening service on a shared platform;

[0014] Receive aerial photography requests sent by users through the client through the monitoring service and verify the requests, including checking the aerial photography area, altitude, angle, and expected aerial photography time parameters in the request;

[0015] The sharing platform extracts key information from the aerial photography request, including the specific location coordinates, expected flight altitude, shooting angle, expected shooting time and user identification, and monitors the real-time status and location of the drone;

[0016] The final drone to perform the mission is determined based on the real-time status and location of the drone, as well as the aerial photography request.

[0017] Furthermore, based on the processing results, the flight route is automatically determined, and aerial photography operations are performed, and the aerial photography data is transmitted to the sharing platform in real time, including:

[0018] Based on the processing results, the sharing platform obtains key information of the aerial photography mission, including the aerial photography target area, expected altitude, and shooting angle, and generates a set of particles representing the flight routes, each of which represents a flight route.

[0019] Define a fitness function for each particle to evaluate the pros and cons of each route to obtain the evaluation result;

[0020] According to the evaluation results, adjust the speed and position of the particles;

[0021] Continue to iterate. When the preset number of iterations is reached, the final flight route is determined according to the fitness value of the particle.

[0022] According to the final flight route, obtain the flight parameters of the drone, including take-off point, flight trajectory, and shooting point;

[0023] The drone performs aerial photography operations according to the final flight route, and during the aerial photography process, the drone transmits the aerial photography data to the sharing platform in real time through wireless communication.

[0024] Furthermore, the fitness value calculation formula of the particle is:

[0025] ;

[0026] in, Represents the fitness value of the particle; , , , represents the weight coefficient; Indicates the total length of the flight path; Indicates the maximum allowed route length; represents the exponential coefficient of the length term; represents the base of natural logarithms; represents the attenuation factor of safety; represents the safety assessment value; Indicates the estimated flight energy consumption; represents the energy consumption budget; Indicates task satisfaction; Indicates the target value of task satisfaction; The exponential coefficient representing the energy consumption term; Indicates the maximum task satisfaction achieved; Represents the exponential coefficient of the task satisfaction term.

[0027] Furthermore, the particle velocity update formula is:

[0028] ;in, Indicates Particles at time speed; represents the inertia weight; Indicates Particles at time speed; , Represent the individual learning rate factor and the group learning rate factor respectively; , Respectively represent random numbers in the range of [0, 1]; Indicates The final historical position of a particle; Indicates Particles at time location; Represents the global final position of all particles; , , represents the weight coefficient; Represents particles In time location; represents the speed difference adjustment coefficient; Represents particles In time speed; Represents particles In time speed; represents the group influence coefficient; Indicates Particles at time location; Indicates Particles at time location; Represents the upper bound of the search space; represents the lower bound of the search space; represents the total number of particles in the particle group; Represents the adjustment coefficient.

[0029] Furthermore, the particle position update formula is:

[0030] ;

[0031] in, Indicates Particles at time location; Indicates Particles at time location; Indicates Particles at time speed; , , represents the weight coefficient; Indicates the target height; Indicates Particles at time Height; Indicates the target angle; Indicates Particles at time Angle represents the target torque; Indicates Particles at time of torque.

[0032] Furthermore, the sharing platform performs color correction, noise removal, and image enhancement operations on the aerial photography data, and sends the processed aerial photography data to the user rights management center, including:

[0033] Transmitting the original aerial data to the sharing platform via wireless communication;

[0034] The sharing platform processes the original aerial photography data, including color correction, noise removal, and image enhancement operations, to obtain processed aerial photography data;

[0035] The processed aerial data is stored in the database, and the sharing platform verifies the authority of the user who requests to view the aerial data;

[0036] If the user authority verification is passed, the sharing platform will send the processed aerial data to the user authority management center.

[0037] In the second aspect, a public area shared drone aerial photography control system includes:

[0038] The acquisition module is used to establish a drone aerial photography sharing platform, including drone scheduling management, flight mission allocation, aerial photography data processing and user authority management functions; the parameters of the initial aerial photography request, such as area, height, angle and time, are encoded as genes; a population is initialized, wherein each individual in the population represents a combination of aerial photography requests; an evaluation function is defined to evaluate the pros and cons of each combination of aerial photography requests according to the importance of the aerial photography area, the influence of the height and angle on the shooting effect, and the suitability of the time window; according to the evaluation function, the individuals in the population are determined to perform crossover and mutation operations until the preset number of iterations is reached to obtain the final aerial photography request;

[0039] The processing module is used for the sharing platform to receive the final aerial photography request and verify the final aerial photography request. After verification, key information is extracted from the final aerial photography request and the final drone to perform the task is determined. If there are multiple aerial photography requests pointing to the same area at the same time, the sharing platform detects and resolves the conflict, allowing the task to continue to be executed to obtain the processing result; based on the processing result, the flight route is automatically determined, and aerial photography operations are performed, and the aerial photography data is transmitted to the sharing platform in real time; the sharing platform performs color correction, noise removal, and image enhancement operations on the aerial photography data, and sends the processed aerial photography data to the user authority management center.

[0040] According to a third aspect, a computing device includes:

[0041] one or more processors;

[0042] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0043] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0044] The above solution of the present invention includes at least the following beneficial effects:

[0045] By establishing a drone aerial photography sharing platform, drone resources can be used more efficiently. The drone scheduling management and flight mission allocation functions ensure that each drone can be used reasonably, avoiding idleness and waste of resources, and also reducing the cost of repeated purchase and maintenance of drones.

[0046] The system can automatically process aerial photography requests and automatically determine the flight route for aerial photography operations based on the processing results. This intelligent and automated management method not only improves work efficiency, but also reduces the possibility of human error and ensures the accuracy and reliability of aerial photography data. Through the user rights management center, the system can ensure that only authorized users can access and process aerial photography data. This mechanism effectively protects the security and privacy of data and avoids illegal acquisition and abuse of data. The sharing platform processes the received aerial photography data, such as color correction and noise removal, to improve the quality and analytical value of the data. The optimized data can be obtained directly without additional post-processing. Through the sharing platform, different users and organizations can share and exchange aerial photography data more conveniently. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart of a method for controlling aerial photography of a shared drone in a public area provided by an embodiment of the present invention.

[0048] Figure 2 It is a schematic diagram of a public area shared drone aerial photography control system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0050] like Figure 1As shown, an embodiment of the present invention provides a method for controlling aerial photography of a shared drone in a public area, the method comprising the following steps:

[0051] Step 1: Establish a drone aerial photography sharing platform, including drone scheduling management, flight mission allocation, aerial photography data processing and user authority management functions;

[0052] Step 2: Encode the parameters of the initial aerial photography request, namely, area, height, angle, and time, into genes; initialize a population, wherein each individual in the population represents an aerial photography request combination; define an evaluation function for evaluating the quality of each aerial photography request combination according to the importance of the aerial photography area, the influence of the height and angle on the shooting effect, and the suitability of the time window; and determine the individuals in the population to perform crossover and mutation operations according to the evaluation function until the preset number of iterations is reached to obtain the final aerial photography request;

[0053] Step 3: The sharing platform receives the final aerial photography request and verifies it. After verification, it extracts key information from the final aerial photography request and determines the final drone that performs the task. If there are multiple aerial photography requests pointing to the same area at the same time, the sharing platform detects and resolves the conflict, allowing the task to continue to be executed to obtain the processing result.

[0054] Step 4: According to the processing results, the flight route is automatically determined, and aerial photography is performed, and the aerial photography data is transmitted to the sharing platform in real time;

[0055] Step 5: The sharing platform performs color correction, noise removal, and image enhancement operations on the aerial photography data, and sends the processed aerial photography data to the user authority management center.

[0056] In the embodiment of the present invention, the unmanned aerial vehicle scheduling and management function is used to realize the effective configuration and scheduling of unmanned aerial vehicle resources, avoiding the idleness and waste of resources. The flight mission allocation function ensures that the aerial photography mission can be timely and accurately allocated to the appropriate unmanned aerial vehicle, thereby improving the response speed and execution efficiency of the mission. The parameters of the aerial photography request are encoded as genes, and the genetic algorithm is used for optimization, so that the final solution can be found from many possible request combinations, meeting the user's personalized needs for the aerial photography area, height, angle and time. This optimization process not only improves the execution efficiency of the aerial photography mission, but also improves the user's experience and satisfaction. After receiving and processing the final aerial photography request, the sharing platform can automatically determine the flight route and perform aerial photography operations, which realizes the intelligence and automation of the aerial photography process. The aerial photography data is transmitted to the sharing platform in real time, ensuring the timeliness and accuracy of the data, and providing users with timely aerial photography information. The sharing platform processes the received aerial photography data, improves the quality and availability of the data, and provides users with more valuable aerial photography results. The user authority management function ensures that only authorized users can access and process the data, protecting the user's data security and privacy rights.

[0057] In a preferred embodiment of the present invention, the above step 1, establishing a drone aerial photography sharing platform, including drone scheduling management, flight mission allocation, aerial photography data processing and user authority management functions, may include:

[0058] The drone dispatch management function is responsible for monitoring the status of all drones connected to the platform, including the location, power, maintenance status, etc. of the drones. When there is a new aerial photography request, the dispatch management system will select a drone to perform the task based on the current location and status of the drone. In addition, it will also be responsible for the takeoff, landing, and flight monitoring of the drone to ensure that the drone flies safely according to the predetermined flight route.

[0059] The flight mission allocation function receives and processes aerial photography requests sent by users through the sharing platform. These requests include parameters such as the aerial photography area, altitude, angle, and time. The mission allocation system intelligently allocates flight missions based on these parameters and the current status of the drone. It takes into account many factors, such as the drone's endurance, the complexity of the flight route, the urgency of the mission, etc., to ensure that each mission can be completed efficiently and accurately.

[0060] The aerial data processing function is responsible for receiving the aerial data transmitted by drones in real time, and preprocessing, storing and analyzing it. Preprocessing may include data cleaning, format conversion, etc. to ensure the quality and availability of the data. The storage process ensures the security and traceability of the data. The analysis stage may involve advanced functions such as image recognition and geographic information processing to extract information of interest to users. The processed data will be sent to users to meet their different needs.

[0061] The user rights management function is responsible for controlling the user's access rights to the sharing platform and its resources. It determines the actions that users can perform and the data they can access based on their roles and permission levels. For example, ordinary users may only be able to send aerial photography requests and view their own aerial photography data, while administrators may have the authority to manage drones, assign flight missions, and view all users' aerial photography data. Through strict rights management, the security of the sharing platform and the confidentiality of data can be ensured.

[0062] In a preferred embodiment of the present invention, in the above step 2, the parameters of the initial aerial photography request, such as the area, height, angle, and time, are encoded as genes; a population is initialized, wherein each individual in the population represents an aerial photography request combination; an evaluation function for evaluating the quality of each aerial photography request combination is defined according to the importance of the aerial photography area, the influence of the height and angle on the shooting effect, and the suitability of the time window; and according to the evaluation function, the individuals in the population are determined to perform crossover and mutation operations until a preset number of iterations is reached to obtain the final aerial photography request, which may include:

[0063] Encode the various parameters of the aerial photography request (area, altitude, angle, time) into genes. Each parameter can be represented as a fixed value, depending on the characteristics and requirements of the parameter. For example:

[0064] Region: Encoded using geographic coordinates (such as longitude and latitude) or predefined region identifiers.

[0065] Altitude: Use a specific value (such as meters or feet) to indicate the altitude at which the drone is flying.

[0066] Angle: Use degrees (such as 0-360 degrees) to indicate the shooting angle of the drone.

[0067] Time: Use timestamp or date time format to indicate the time of the aerial photography.

[0068] Combine these parameters in a certain order to form a gene string, which represents a specific aerial photography request. Initialize a population, where each individual represents a combination of aerial photography requests. The size of the population can be set as needed, including multiple individuals to ensure that the genetic algorithm has enough diversity for searching. Each individual consists of a set of genes, that is, a set of specific area, height, angle and time parameters.

[0069] In order to evaluate the pros and cons of each combination of aerial photography requests, an evaluation function is defined as: ;in, Indicates the final scoring result; represents the regional importance score; A weight indicating the importance of the region; indicates a high suitability score; weights indicating high suitability; Indicates the angle optimization score; The weight representing the degree of angle optimization; represents the time suitability score; Represents the weight of temporal suitability. This function can score the gene string of each individual according to the goals and requirements of the aerial photography task. The evaluation function can consider multiple factors, such as the importance of the aerial photography area, the impact of height and angle on the shooting effect, the suitability of the time window, etc. The function can return a numerical score indicating the pros and cons of the individual under the current task. According to the score of the evaluation function, genetic operations are performed on the individuals in the population, including crossover and mutation. Two individuals are selected as parents, and new offspring individuals are generated by exchanging some of their genes. The crossover operation can retain the excellent genes of the parent individuals while introducing new gene combinations. Some genes of the individual are randomly modified to introduce new gene mutations. The mutation operation can increase the diversity of the population and help explore new solution spaces.

[0070] The high suitability score confirmation process is as follows:

[0071] According to the specific requirements of the aerial photography task, determine an appropriate altitude range. This range is based on factors such as the characteristics of the object being photographed, the required image resolution, and safety considerations. For each individual (i.e., each combination of aerial photography requests), check whether its altitude parameter falls within this appropriate range. If the altitude parameter is within the appropriate range, a corresponding score is assigned based on how close it is to the ideal altitude. For example, a mathematical method of linear interpolation can be used to calculate this score, so that the closer it is to the ideal altitude, the higher the score. If the altitude parameter exceeds the appropriate range, a lower score or penalty is given.

[0072] The angle optimization score confirmation process is as follows:

[0073] According to the goal of the aerial photography task and the characteristics of the photographed object, one or more optimized shooting angles are determined, which may be designed to capture a specific view of the object and maximize the information content in the image. For each individual in the population, the degree of match between its angle parameters and the optimized angle is evaluated, which can be achieved by using a similarity metric (such as cosine similarity). According to the degree of match, the corresponding score is assigned, so that individuals that are more consistent with the optimized angle receive a higher score. The process of confirming the time suitability score is as follows:

[0074] According to the requirements of the aerial photography task, such as lighting conditions, weather conditions, activity time of the target object, etc., one or more suitable time windows are determined. These time windows can be specific start and end times, such as "9 am to 11 am" or "4 pm to 6 pm". For each individual (aerial photography request combination), its time parameter is extracted, that is, the specific time when the aerial photography is planned. If this time parameter falls within the appropriate time window, its proximity to the ideal time within the window is calculated. The ideal time can be the center point of the window. The degree of proximity can be measured by calculating the time difference, for example, using an absolute time difference (in minutes or hours) or a relative time difference (as a percentage of the total length of the time window).

[0075] The corresponding score is assigned according to the degree of proximity, for example, using linear interpolation, where the minimum time difference corresponds to the highest score, the maximum acceptable time difference corresponds to the lowest score (but still a positive value), and a penalty is imposed if the maximum acceptable time difference is exceeded. For example, if the time window is 2 hours, the minimum time difference is 0 minutes (i.e., it is completely consistent with the ideal time), and the maximum acceptable time difference is 30 minutes. If the individual's time parameters are not within any suitable time window, a lower score or penalty value is directly given to reflect the individual's lack of time suitability.

[0076] Repeat the evaluation, crossover, and mutation operations until the preset number of iterations is reached. In each iteration, individuals are selected for crossover and mutation based on the scores of the evaluation function to generate a new offspring population. Through continuous iterative optimization, the individuals in the population will gradually approach the final solution. When the preset number of iterations is reached, individuals are selected based on the scores, and the selected individuals are used as the final aerial photography request. The final aerial photography request is output to the sharing platform or user. This request contains the optimized area, height, angle, and time parameters, which can meet the personalized needs of users and improve the execution efficiency and shooting effect of aerial photography tasks.

[0077] In a preferred embodiment of the present invention, in the above step 3, the sharing platform receives the final aerial photography request and verifies the final aerial photography request. After verification, the sharing platform extracts key information from the final aerial photography request and determines the final drone that performs the task. If there are multiple aerial photography requests pointing to the same area at the same time, the sharing platform detects and resolves the conflict, so that the task continues to be executed to obtain the processing result, which may include:

[0078] Step 33, setting up a monitoring service on the sharing platform;

[0079] Step 34, receiving the aerial photography request sent by the user through the client through the monitoring service, and verifying the request, including checking the aerial photography area, altitude, angle and expected aerial photography time parameters in the request;

[0080] Step 35, the sharing platform extracts key information from the aerial photography request, including the specific location coordinates of the aerial photography, the expected flight altitude, the shooting angle, the expected shooting time and the user identity, and monitors the real-time status and location of the drone;

[0081] Step 36, determining the final drone to perform the mission according to the real-time status and location of the drone and the aerial photography request;

[0082] Step 37: If there are multiple aerial photography requests directed to the same area at the same time, the shared platform detects and resolves the conflict, allowing the task to continue to execute to obtain the processing result.

[0083] In an embodiment of the present invention, the sharing platform first sets up a continuously running monitoring service, which is specifically responsible for receiving aerial photography requests from user clients. This monitoring service is a bridge for communication between the platform and users, ensuring that user requests can be captured by the platform in real time. When users send aerial photography requests through the client, the monitoring service will immediately receive these requests. After receiving the request, the system will verify whether the parameters contained in the request, such as the aerial photography area, altitude, angle, and expected aerial photography time, are valid.

[0084] After verification, the sharing platform will extract key information from the request, such as the specific location coordinates of the aerial photography, the expected flight altitude, the shooting angle, the expected shooting time, and the user's identity. At the same time, the platform will also monitor the real-time status and location of the drone to ensure the accuracy and feasibility of subsequent task assignments. Based on the extracted key information and the current status and location of the drone, the sharing platform will intelligently select the drone to perform the task. This selection process takes into account factors such as the drone's endurance, distance from the target area, and current task load.

[0085] If there are multiple aerial photography requests directed at the same area at the same time, the sharing platform will detect and resolve these conflicts. It will ensure that all tasks can be executed smoothly by optimizing flight routes, adjusting shooting times, or reallocating drone resources. Finally, the platform will output a processing result that clearly defines which drones will perform which tasks, as well as the execution order and schedule of the tasks.

[0086] By setting up a continuously running monitoring service, the sharing platform can instantly receive and process users' aerial photography requests, ensuring the real-time and efficient performance of the tasks. By verifying the request parameters and extracting key information, the platform can ensure that the received requests are accurate and executable, thereby improving the success rate of task execution.

[0087] The sharing platform can intelligently select the most suitable drone for the task and resolve task conflicts based on actual conditions, thus realizing intelligent and automated task allocation and improving the utilization rate of drones.

[0088] When specifically applied, this includes:

[0089] Step 33, configure a monitoring service on the shared platform to ensure that the service can continue to run and monitor aerial photography requests from user clients, such as through SSL / TLS encrypted communication to prevent data leakage or tampering.

[0090] Step 34: After receiving the aerial photography request sent by the user through the client, the monitoring service first performs basic network communication verification to ensure that the request comes from a legitimate user client. Verify the parameters in the request, including the aerial photography area, altitude, angle, and expected aerial photography time, to ensure that these parameters are within a reasonable range and comply with relevant regulations. If the request parameters are invalid or unreasonable, the monitoring service will reject the request; otherwise, it will accept the request and prepare for subsequent processing.

[0091] Step 35, extract key information from the verified aerial photography request, such as the specific location coordinates of the aerial photography, the expected flight altitude, the shooting angle, the expected shooting time and the user identity, etc.; the sharing platform monitors the status and location of the available drones in real time, including the drone's battery level, signal strength, current location, etc.; ensure that the extracted request information and the drone's real-time status data are kept updated synchronously on the sharing platform.

[0092] Step 36, based on the real-time location and status of the drone and the specific requirements of the aerial photography request, determine the drone that is most suitable for performing the task; assign the aerial photography task to the selected drone, and update the drone's task list and status information; send the task instruction to the selected drone, including the specific location, altitude, angle and time of the aerial photography. For example, first check the current location of each drone, calculate the time and path required for them to reach the aerial photography area, and drones closer to the aerial photography area will be given priority because this can reduce flight time and energy consumption; the current status of the drone includes its battery, flight stability, signal connection quality, etc. For example, a drone with sufficient battery is more suitable for performing the task than a drone that is about to run out of battery. Analyze the specific requirements in the aerial photography request, such as shooting altitude, angle, time, etc., to ensure that the selected drone can meet these specific conditions. For example, if the request requires high-altitude photography, drones that can fly to higher altitudes will be given priority.

[0093] Step 37, if there are multiple aerial photography requests pointing to the same area at the same time, the sharing platform will detect whether there are conflicts between these requests, such as time conflicts, space conflicts, etc.; once a conflict is detected, the sharing platform will resolve these conflicts according to the preset conflict resolution strategy (such as priority sorting) to ensure that each request can be properly processed; the processing results will be fed back to the user client, including whether the task is successfully assigned, the expected start time of the aerial photography, and other information. At the same time, the task status and drone status information on the sharing platform are updated. Through these steps, the sharing platform can efficiently receive, verify and process users' aerial photography requests, ensuring that each request can receive a timely and reasonable response.

[0094] For example, when specifically applied, it specifically includes:

[0095] The shared drone platform has received multiple aerial photography requests and now needs to reasonably allocate tasks based on the drone’s real-time location, status, and specific requirements of the aerial photography requests.

[0096] Specific implementation of step 36:

[0097] The sharing platform received three aerial photography requests, each requesting aerial photography at different times and locations; there are five drones on the platform, each with its own unique performance parameters and current status (such as battery level, location, etc.); taking into account the distance between the current location of the drone and the aerial photography location, the remaining battery level of the drone, flight stability, and the height, angle, and time requirements in the aerial photography request, the algorithm selected three drones that are most suitable for performing the three aerial photography tasks; the platform assigned each aerial photography task to the three selected drones, and the task list of each drone was updated, adding new aerial photography tasks, and displaying the detailed information and priority of the tasks. At the same time, the status information of the drones was also updated, showing their current tasks, estimated completion time, and real-time status during task execution. For each selected drone, the platform sent detailed task instructions.

[0098] For example, for one of the drones, the instructions might be as follows: "Fly to coordinates (XX.XXXX, YY.YYYY), at an altitude of 100 meters, and take pictures of the event site at a 45-degree angle. The shooting time is from 3pm to 3:30pm." These instructions ensure that the drone can accurately reach the specified location and take pictures at the correct angle and altitude.

[0099] In a preferred embodiment of the present invention, the above step 4, automatically determining the flight route according to the processing result, performing the aerial photography operation, and transmitting the aerial photography data to the sharing platform in real time, may include:

[0100] Step 44, the sharing platform obtains key information of the aerial photography mission according to the processing results, including the aerial photography target area, the expected height, and the shooting angle, and generates a group of particles representing the flight routes, each particle representing a flight route;

[0101] Step 45, defining a fitness function for each particle to evaluate the quality of each route to obtain an evaluation result;

[0102] Step 46, adjusting the speed and position of the particle according to the evaluation result;

[0103] Step 47, continue iterating, and when the preset number of iterations is reached, determine the final flight route according to the fitness value of the particle;

[0104] Step 48, according to the final flight route, obtain the flight parameters of the UAV, including the take-off point, flight trajectory, and shooting point;

[0105] Step 49, the drone performs aerial photography according to the final flight route, and during the aerial photography process, the drone transmits the aerial photography data to the sharing platform in real time via wireless communication.

[0106] In an embodiment of the present invention, the sharing platform extracts key information of the aerial photography task, such as the aerial photography target area, expected height and shooting angle, based on the processing results. Based on this information, the platform generates a set of particles representing possible flight routes, each of which essentially represents a flight route plan. In order to evaluate the pros and cons of each flight route, the platform defines a fitness function for each particle. This function comprehensively considers multiple factors, such as the safety, efficiency, energy consumption, etc. of the flight route to quantify the performance of each route. Through this function, the platform evaluates each flight route and obtains the evaluation results. According to the evaluation results, the platform adjusts the speed and position of the particles. This process will continue to iterate, and each iteration will optimize the state of the particles until the preset number of iterations is reached. Finally, the platform will select the final flight route based on the fitness values ​​of all particles. After determining the final flight route, the platform will obtain the specific flight parameters of the drone, including the take-off point, detailed flight trajectory and shooting point. Subsequently, the drone will perform precise aerial photography operations according to these parameters. During the aerial photography process, the drone transmits the captured data back to the sharing platform in real time through wireless communication technology.

[0107] The particle swarm optimization algorithm can automatically find the optimal flight route, which not only improves the efficiency of aerial photography, but also enhances the safety of flight. During the flight, if the environment changes or encounters an emergency, the algorithm can adjust the flight route in real time to ensure the smooth completion of the mission. During the aerial photography process, the drone transmits data to the sharing platform in real time, which ensures the timeliness and accuracy of the data and facilitates users to obtain and analyze aerial photography data in a timely manner. Through intelligent flight route planning and real-time data transmission, drone resources can be used more effectively and unnecessary flight and waiting time can be reduced.

[0108] In a preferred embodiment of the present invention, the fitness value calculation formula of the particle is:

[0109] ;

[0110] in, Represents the fitness value of the particle; , , , represents the weight coefficient; Indicates the total length of the flight path; Indicates the maximum allowed route length; represents the exponential coefficient of the length term; represents the base of natural logarithms; represents the attenuation factor of safety; represents the safety assessment value; Indicates the estimated flight energy consumption; represents the energy consumption budget; Indicates task satisfaction; Indicates the target value of task satisfaction; The exponential coefficient representing the energy consumption term; Indicates the maximum task satisfaction achieved; Represents the exponential coefficient of the task satisfaction term.

[0111] In an embodiment of the present invention, F It is a comprehensive indicator for evaluating the quality of particles (i.e. flight route plans). It is calculated by weighted combination of various key factors of the flight route (such as length, safety, energy consumption, and mission satisfaction). The higher the fitness value, the better the flight route. , , , The weight coefficient is used to balance and adjust the importance of different evaluation dimensions in the fitness value calculation. Each coefficient corresponds to an evaluation dimension (length, safety, energy consumption, task satisfaction), and the value reflects the priority of the corresponding dimension in the optimization process. By adjusting these coefficients, flexible adaptation to different task requirements can be achieved. L Represents the actual length of the flight path. The maximum allowed length of the flight path is set as the optimization constraint. L and , which can ensure that the selected flight route meets the mission requirements while shortening the flight distance and improving flight efficiency. Used to control the nonlinear effect of the length factor in the fitness value calculation. The value of can change the sensitivity of the length factor to the fitness value, thereby affecting the directionality and speed of the optimization algorithm in the search process. e is the base of the natural logarithm and is related to the security attenuation coefficient k and safety assessment value S Together they constitute the safety assessment item. Here, an exponential decay function is used to quantify safety, that is, as the safety assessment value S As increases, the value of its corresponding item will decrease rapidly, thus ensuring that the flight route has sufficient safety.

[0112] E It represents the estimated energy consumption of the flight route and is an important indicator for evaluating flight economy. The energy consumption budget is set. E and , which can ensure that the selected flight route reduces energy costs while meeting mission requirements. Used to adjust the influence of energy consumption factors in fitness value calculation. The value of can change the contribution of energy consumption to the fitness value, so as to more accurately weigh the relationship between energy consumption and other factors during the optimization process. T , and (Mission satisfaction, mission satisfaction target value and maximum mission satisfaction achieved) These three are used together to quantitatively evaluate the adaptability and completion of the flight route to the mission. It is used to control the nonlinear effect of task satisfaction factors in the fitness value calculation. The value of can change the sensitivity of task satisfaction to the fitness value, so as to more accurately pursue the achievement of task goals during the optimization process.

[0113] This formula takes into account multiple key factors such as flight route length, safety, energy consumption, and mission satisfaction, and helps find flight route solutions that are excellent in multiple dimensions. , , , , the importance of a certain evaluation dimension can be emphasized or weakened according to the task requirements. This flexibility enables the formula to adapt to the optimization needs in different scenarios. , , and safety attenuation factor , taking into account the nonlinear impact of each evaluation dimension. S This helps avoid choosing riskier flight routes, thereby improving the overall safety of the flight. The formula also takes into account the expected flight energy consumption. E and task satisfaction T , which helps to find the balance between energy consumption and task satisfaction during the optimization process. By setting the maximum allowed route length , Energy budget and the maximum task satisfaction achieved , provides a clear goal orientation for the optimization process. This helps ensure that the selected flight path is close to or reaches the preset target value while satisfying the constraints.

[0114] Among them, the safety assessment value S The specific calculation formula is:

[0115] ;

[0116] in, , , and is the weight coefficient; is the distance between the drone and the nearest obstacle; It is the minimum safe distance that allows the drone to approach obstacles; is the flight altitude of the drone; is the maximum permitted flight altitude; is the flight speed of the drone; is the maximum flight speed allowed; is the current battery level of the drone; It is the maximum charge of the drone battery.

[0117] By considering factors such as the distance between the drone and obstacles, flight altitude, flight speed, and battery power, the safety of the drone can be comprehensively evaluated to avoid potential collision and crash risks. By calculating the safety assessment value of the drone in real time and adjusting the flight route and speed of the drone according to this value, it can adapt to different aerial photography environments and mission requirements. By optimizing the flight route and speed of the drone, the aerial photography time can be shortened and the efficiency of aerial photography can be improved, while avoiding unnecessary energy consumption and extending the drone's flight time. By considering the impact of multiple factors on the safety of the drone and adjusting the flight status of the drone in real time, it can ensure that the drone maintains a stable flight state in a complex environment and improve the reliability and stability of aerial photography.

[0118] In a preferred embodiment of the present invention, the particle velocity update formula is:

[0119] ;in, Indicates Particles at time speed; represents the inertia weight; Indicates Particles at time speed; , Represent the individual learning rate factor and the group learning rate factor respectively; , Respectively represent random numbers in the range of [0, 1]; Indicates The final historical position of a particle; Indicates Particles at time location; Represents the global final position of all particles; , , represents the weight coefficient; Represents particles In time location; represents the speed difference adjustment coefficient; Represents particles In time speed; Represents particles In time speed; represents the group influence coefficient; Indicates Particles at time location; Indicates Particles at time location; Represents the upper bound of the search space; represents the lower bound of the search space; represents the total number of particles in the particle group; Represents the adjustment coefficient.

[0120] In an embodiment of the present invention, and These two parameters represent the particle At the moment and time t The speed of the particle determines its moving direction and step size in the search space, and the inertia weight Determines the degree to which the particle's current velocity affects its velocity at the next moment. , the convergence speed and search accuracy of the algorithm can be controlled. represents the individual learning rate factor, and Represents the group learning rate factor. These two parameters balance the impact of individual experience and group experience on particle movement.

[0121] A random number in the range [0, 1] , , used to increase the diversity of the search. The final position of the particle's history Recording particles The final position found during the search. The particle will tend to move towards this position in order to find a solution. Represents the current position of the particle in the search space. The particle's position is updated based on the velocity to explore the search space and find the final solution. is the final global position, and the particles will be attracted by the final global position, thereby accelerating the convergence to the final solution. , , These coefficients are used to adjust the weights of different parts of the velocity update formula. They find a balance between global and local search.

[0122] , and Used to introduce historical information of particles to better remember and utilize past search experience. They can affect the current speed and future movement direction of particles. Speed ​​difference adjustment coefficient , which is used to adjust the difference between the current speed of the particle and the past speed. By adjusting this coefficient, the dynamic behavior of the particle during the search process can be controlled. Group influence coefficient Reflects the influence of other particles on the current particle. represents the positions of other particles, and Together they are used to calculate the influence of the group on the current particle. This helps particles share information and improves search efficiency. Indicates the size of the particle swarm. N Values ​​can increase the diversity of the search. Adjustment factor The weight used to adjust the last part of the formula involves adjusting the position and speed of the particle. , you can control the degree of influence of this part on the particle velocity update.

[0123] By adjusting the inertia weight , able to find a balance between global search and local search. represents the particle's learning of its final historical position, and Represents the particle's learning of the group's final position. This combination enables the particle to use both individual and group experience to guide the search, improving search efficiency. and The introduction of increases the randomness and diversity of the search, helps to prevent particles from falling into the local optimal solution too early, and improves the global optimization ability of the algorithm.

[0124] By introducing and ,The formula takes into account the historical position and velocity changes of the particles, which helps the particles to maintain a certain inertia during the search process, while making adaptive adjustments based on historical information. It reflects the collaboration and information sharing between particles. Particles adjust their movement direction by sensing the positions of other particles, which helps to enhance the overall optimization ability of the particle swarm. The boundary of the search space is taken into account. When the particle approaches the boundary of the search space, this part will play an adjustment role to prevent the particle from touching the boundary too early and falling into the local optimum. It also helps the particle move to the central area of ​​the search space to explore more solutions.

[0125] In a preferred embodiment of the present invention, the particle position update formula is:

[0126] ;

[0127] in, Indicates Particles at time location; Indicates Particles at time location; Indicates Particles at time speed; , , represents the weight coefficient; Indicates the target height; Indicates Particles at time Height; Indicates the target angle; Indicates Particles at time Angle represents the target torque; Indicates Particles at time of torque.

[0128] In an embodiment of the present invention, Represents the position of the particle at the next moment, which is determined by the current position , the speed at the next moment , and the difference from the target state (height, angle, torque). is the current position of the particle, which serves as the starting point for position updates. Indicates the speed of the particle at the next moment, which determines the direction and distance the particle moves from its current position. , , are weight coefficients, which adjust the influence of height difference, angle difference and torque difference on position update respectively. The setting of these coefficients allows the algorithm to find a balance between global search and local fine-tuning. Reflects the difference between the particle's current height and the target height. Multiplied by the weight coefficient Finally, this difference is used to adjust the particle's position to move it toward the target height. Indicates the deviation between the particle's current angle and the target angle. By multiplying the weight coefficient , this difference is taken into account in the position update to guide the particle to adjust to the target angle. It reflects the inconsistency between the particle's current torque and the target torque. Multiply by the weight coefficient Finally, this difference also affects the particle's position update, helping the particle adjust to the torque difference.

[0129] By comprehensively considering the particle's current position, speed, and the difference from the target state (height, angle, torque), the formula can accurately calculate and update the particle's new position. This mechanism enables particles to explore and optimize more effectively in the search space, thereby improving search efficiency. Weight coefficient ( , , ) can adjust the degree of influence of different factors on particle movement. By setting these coefficients, a balance between global search and local search can be achieved. This helps particles explore more solutions globally while performing fine searches in local areas to find the final solution. The difference between the current state of the particle and the target state includes height difference, angle difference, and torque difference. These difference values ​​are used to adjust the particle's position update so that the particle can move to the target state more accurately. This helps to accelerate the convergence of the algorithm.

[0130] In a preferred embodiment of the present invention, in the above step 5, the sharing platform performs color correction, noise removal, and image enhancement operations on the aerial photography data, and sends the processed aerial photography data to the user rights management center, including:

[0131] Step 52, transmitting the original aerial photography data to the sharing platform via wireless communication;

[0132] Step 53, the sharing platform processes the original aerial photography data, including color correction, noise removal, and image enhancement operations, to obtain processed aerial photography data;

[0133] Step 54, storing the processed aerial data in a database, and at the same time, the sharing platform verifies the authority of the user who requests to view the aerial data;

[0134] Step 55: If the user authority verification is passed, the sharing platform sends the processed aerial photography data to the user authority management center.

[0135] In an embodiment of the present invention, the aerial photography device transmits the original aerial photography data to the sharing platform via wireless communication (Wi-Fi). After receiving the original aerial photography data, the sharing platform will perform a series of processing operations, including color correction, noise removal, image enhancement, etc. The processed aerial photography data will be stored in the database, and the sharing platform will verify the authority of the user who requests to view the aerial photography data. This step is a key link in data security and privacy protection, ensuring that only authorized users can access sensitive data.

[0136] Once the user's rights are verified, the sharing platform will send the processed aerial data to the User Rights Management Center. The User Rights Management Center acts as an intermediate hub, responsible for receiving and distributing data to ensure that the data can reach the end user safely and efficiently.

[0137] Through operations such as color correction, noise removal, and image enhancement, the sharing platform can improve the quality and clarity of aerial data. Through a strict user authority verification mechanism, the sharing platform can ensure that only authorized users can access and process aerial data. This effectively prevents data leakage and abuse and protects the security and privacy of data. By storing processed aerial data in a database and establishing a data distribution mechanism (such as a user authority management center), the sharing platform can ensure that the data can reach the end user quickly and accurately. This improves the efficiency of data utilization and reduces delays in data transmission and processing. The establishment of a sharing platform promotes data sharing and collaboration among different users. By sharing high-quality aerial data, different users can more conveniently exchange information and share knowledge.

[0138] When specifically applied, this includes:

[0139] Step 52, establish a stable wireless communication connection between the UAV and the sharing platform through Wi-Fi, 4G / 5G network or other wireless communication technologies; after completing the aerial photography mission, the UAV transmits the captured original aerial photography data (such as photos, videos, etc.) to the sharing platform in real time through the established wireless communication connection; the sharing platform is equipped with a corresponding data receiving interface for receiving the original aerial photography data transmitted by the UAV.

[0140] Step 53, color balance and correction are performed on the received raw aerial data to ensure the color accuracy and consistency of the image, which specifically involves adjusting parameters such as the color temperature, hue and saturation of the image; due to the influence of factors such as the shooting environment and equipment performance, the aerial image may contain noise. This step uses image denoising algorithms (such as median filtering, Gaussian filtering, etc.) to reduce or eliminate these noise points and improve image quality. In order to further improve the visual effect and information content of the aerial image, image enhancement operations such as contrast enhancement and sharpening are performed. These operations can highlight the details in the image, making it clearer and easier to analyze.

[0141] In step 54, the processed aerial data is stored in the database of the sharing platform for subsequent access and analysis. The database design should ensure the security and scalability of the data; when a user requests to view the aerial data, the sharing platform will first verify the user's permissions, specifically involving checking the user's identity authentication information (such as user name, password) and their role or permission level in the system.

[0142] Step 55, once the user passes the authority verification, the sharing platform will confirm that the user has the right to access the requested aerial data; the sharing platform will send the processed aerial data to the user authority management center, which is usually a secure data exchange area where users can download or view their data; in order to ensure data security and track data usage, the sharing platform may record detailed information on each data access, including access time, accessing user, and accessed data content.

[0143] Through these steps, the sharing platform can ensure the secure transmission, effective processing and controlled access of aerial data, thus providing users with an efficient, reliable and secure aerial data sharing service.

[0144] like Figure 2 As shown, an embodiment of the present invention further provides a public area shared drone aerial photography control system 20, comprising:

[0145] The acquisition module 21 is used to establish a drone aerial photography sharing platform, including drone scheduling management, flight mission allocation, aerial photography data processing and user authority management functions; the parameters of the initial aerial photography request, such as area, height, angle and time, are encoded as genes; a population is initialized, wherein each individual in the population represents an aerial photography request combination; an evaluation function for evaluating the quality of each aerial photography request combination is defined according to the importance of the aerial photography area, the influence of the height and angle on the shooting effect, and the suitability of the time window; according to the evaluation function, the individuals in the population are determined to perform crossover and mutation operations until a preset number of iterations is reached to obtain the final aerial photography request;

[0146] The processing module 22 is used for the shared platform to receive the final aerial photography request and verify the final aerial photography request. After verification, key information is extracted from the final aerial photography request and the final drone to perform the task is determined. If there are multiple aerial photography requests pointing to the same area at the same time, the shared platform detects and resolves the conflict, so that the task continues to be executed to obtain the processing result; according to the processing result, the flight route is automatically determined, and the aerial photography operation is performed, and the aerial photography data is transmitted to the shared platform in real time; the shared platform performs color correction, noise removal, and image enhancement operations on the aerial photography data, and sends the processed aerial photography data to the user authority management center.

[0147] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0148] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0149] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0150] The above is a preferred embodiment of the present invention. 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 invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for controlling aerial photography of a shared drone in a public area, characterized in that: The method comprises: Establish a drone aerial photography sharing platform, including drone dispatch management, flight mission allocation, aerial photography data processing and user authority management functions; Encode the parameters of the initial aerial photography request, such as area, height, angle, and time, into genes; initialize a population, where each individual in the population represents an aerial photography request combination; define an evaluation function for evaluating the quality of each aerial photography request combination according to the importance of the aerial photography area, the impact of the height and angle on the shooting effect, and the suitability of the time window; determine the individuals in the population to perform crossover and mutation operations according to the evaluation function until the preset number of iterations is reached to obtain the final aerial photography request, which may include: Encode the various parameters of the aerial photography request, such as area, height, angle and time, into genes; each parameter is represented as a fixed value; combine the parameters in sequence to form a gene string, which represents a specific aerial photography request; initialize a population, in which each individual represents a combination of aerial photography requests; each individual is composed of a set of genes, i.e., a set of specific area, height, angle and time parameters; In order to evaluate the pros and cons of each combination of aerial photography requests, an evaluation function is defined as: ;in, Indicates the final scoring result; represents the regional importance score; A weight indicating the importance of the region; indicates a high suitability score; weights indicating high suitability; Indicates the angle optimization score; The weight representing the degree of angle optimization; represents the time suitability score; The weight represents the time suitability; the evaluation function can score the gene string of each individual according to the goals and requirements of the aerial photography task; according to the score of the evaluation function, genetic operations are performed on the individuals in the population, including crossover and mutation; two individuals are selected as parents, and new offspring individuals are generated by exchanging some genes of the two individuals; the evaluation, crossover and mutation operations are repeated until the preset number of iterations is reached; in each iteration, individuals are selected according to the score of the evaluation function for crossover and mutation to generate a new offspring population; through continuous iterative optimization, the individuals in the population will gradually approach the final solution; when the preset number of iterations is reached, individuals are selected according to the score, and the selected individuals are used as the final aerial photography request; The sharing platform receives the final aerial photography request and verifies it. After verification, it extracts key information from the final aerial photography request and determines the final drone that will perform the task. If there are multiple aerial photography requests pointing to the same area at the same time, the sharing platform detects and resolves the conflict, allowing the task to continue to be executed to obtain the processing result. According to the processing results, the flight route is automatically determined, and aerial photography operations are performed, and the aerial photography data is transmitted to the sharing platform in real time; The sharing platform performs color correction, noise removal, and image enhancement operations on the aerial photography data, and sends the processed aerial photography data to the user authority management center.

2. The public area shared drone aerial photography control method according to claim 1 is characterized in that: The sharing platform receives the final aerial photography request and verifies it. After verification, it extracts key information from the final aerial photography request and determines the final drone to perform the mission, including: Set up a listening service on a shared platform; Receive aerial photography requests sent by users through the client through the monitoring service and verify the requests, including checking the aerial photography area, altitude, angle, and expected aerial photography time parameters in the request; The sharing platform extracts key information from the aerial photography request, including the specific location coordinates, expected flight altitude, shooting angle, expected shooting time and user identification, and monitors the real-time status and location of the drone; The final drone to perform the mission is determined based on the real-time status and location of the drone, as well as the aerial photography request.

3. The public area shared drone aerial photography control method according to claim 2 is characterized in that: According to the processing results, the flight route is automatically determined, and aerial photography operations are performed, and the aerial photography data is transmitted to the sharing platform in real time, including: Based on the processing results, the sharing platform obtains key information of the aerial photography mission, including the aerial photography target area, expected altitude, and shooting angle, and generates a set of particles representing the flight routes, each of which represents a flight route. Define a fitness function for each particle to evaluate the pros and cons of each route to obtain the evaluation result; According to the evaluation results, adjust the speed and position of the particles; Continue to iterate. When the preset number of iterations is reached, the final flight route is determined according to the fitness value of the particle. According to the final flight route, obtain the flight parameters of the drone, including take-off point, flight trajectory, and shooting point; The drone performs aerial photography operations according to the final flight route, and during the aerial photography process, the drone transmits the aerial photography data to the sharing platform in real time through wireless communication.

4. The public area shared drone aerial photography control method according to claim 3 is characterized in that: The fitness value calculation formula of a particle is: ； in, Represents the fitness value of the particle; , , , represents the weight coefficient; Indicates the total length of the flight path; Indicates the maximum allowed route length; represents the exponential coefficient of the length term; represents the base of natural logarithms; represents the attenuation factor of safety; represents the safety assessment value; Indicates the estimated flight energy consumption; represents the energy consumption budget; Indicates task satisfaction; Indicates the target value of task satisfaction; The exponential coefficient representing the energy consumption term; Indicates the maximum task satisfaction achieved; Represents the exponential coefficient of the task satisfaction term.

5. The public area shared drone aerial photography control method according to claim 4 is characterized in that: The particle velocity update formula is: ； in, Indicates Particles at time speed; represents the inertia weight; Indicates Particles at time speed; , Represent the individual learning rate factor and the group learning rate factor respectively; , Respectively represent random numbers in the range of [0, 1]; Indicates The final historical position of a particle; Indicates Particles at time location; Represents the global final position of all particles; , , represents the weight coefficient; Represents particles In time location; represents the speed difference adjustment coefficient; Represents particles In time speed; Represents particles In time speed; represents the group influence coefficient; Indicates Particles at time location; Indicates Particles at time location; Represents the upper bound of the search space; represents the lower bound of the search space; represents the total number of particles in the particle group; Represents the adjustment coefficient.

6. The public area shared drone aerial photography control method according to claim 5 is characterized in that: The particle position update formula is: ； in, Indicates Particles at time location; Indicates Particles at time location; Indicates Particles at time speed; , , represents the weight coefficient; Indicates the target height; Indicates Particles at time Height; Indicates the target angle; Indicates Particles at time Angle represents the target torque; Indicates Particles at time of torque.

7. The public area shared drone aerial photography control method according to claim 6 is characterized in that: The sharing platform performs color correction, noise removal, and image enhancement operations on the aerial photography data, and sends the processed aerial photography data to the user rights management center, including: Transmitting the original aerial data to the sharing platform via wireless communication; The sharing platform processes the original aerial photography data, including color correction, noise removal, and image enhancement operations, to obtain processed aerial photography data; The processed aerial data is stored in the database, and the sharing platform verifies the authority of the user who requests to view the aerial data; If the user authority verification is passed, the sharing platform will send the processed aerial data to the user authority management center.

8. A public area shared drone aerial photography control system, characterized in that: Applied to the method according to any one of claims 1 to 7, comprising: The acquisition module is used to establish a drone aerial photography sharing platform, including drone scheduling management, flight mission allocation, aerial photography data processing and user authority management functions; the parameters of the initial aerial photography request, such as area, height, angle and time, are encoded as genes; a population is initialized, wherein each individual in the population represents a combination of aerial photography requests; an evaluation function is defined to evaluate the pros and cons of each combination of aerial photography requests according to the importance of the aerial photography area, the influence of the height and angle on the shooting effect, and the suitability of the time window; according to the evaluation function, the individuals in the population are determined to perform crossover and mutation operations until the preset number of iterations is reached to obtain the final aerial photography request; The processing module is used for the sharing platform to receive the final aerial photography request and verify the final aerial photography request. After verification, key information is extracted from the final aerial photography request and the final drone to perform the task is determined. If there are multiple aerial photography requests pointing to the same area at the same time, the sharing platform detects and resolves the conflict, allowing the task to continue to be executed to obtain the processing result; based on the processing result, the flight route is automatically determined, and aerial photography operations are performed, and the aerial photography data is transmitted to the sharing platform in real time; the sharing platform performs color correction, noise removal, and image enhancement operations on the aerial photography data, and sends the processed aerial photography data to the user authority management center.

9. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images