Unmanned aerial vehicle cluster fire monitoring method based on dynamic Voronoi diagram
Through the dynamic Voronoi diagram and real-time event-driven drone swarm monitoring method, the problems of response hysteresis and poor anti-destruction performance in drone swarm fire monitoring are solved, continuous coverage and rapid response of fire boundaries are achieved, and the system's adaptability and mission stability are improved.
Patent Information
- Application Number
- CN202510814105.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-18
- Publication Date
- 2025-09-12
AI Technical Summary
Existing drone swarm fire monitoring methods have slow responses when fire boundaries change dynamically, have insufficient coverage, and have poor anti-destruction capabilities. They are unable to adapt in a timely manner to emergencies such as fire boundary expansion, splitting, merging, or drone damage.
A UAV cluster fire monitoring method based on dynamic Voronoi diagram is adopted. By monitoring fire events in real time and dynamically updating Voronoi cells, local reconstruction and UAV path planning are achieved by combining cluster head real-time perception and event judgment, and the flight altitude is dynamically adjusted to maximize coverage quality.
It achieves continuous tracking and coverage of fire boundaries, improves response efficiency and anti-destruction capabilities, and ensures real-time monitoring and mission continuity in the fire area.
Smart Images
Figure CN120636064A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of drone applications, and in particular to a drone cluster fire monitoring method based on a dynamic Voronoi diagram. Background Art
[0002] Existing fire monitoring methods primarily rely on fixed cameras, satellite remote sensing, or single drone patrols. These methods suffer from slow response, insufficient coverage, and poor survivability. In recent years, drone swarm collaborative monitoring technology has rapidly developed, and Voronoi diagrams, due to their inherent advantages in area demarcation, have been introduced to the field of coverage control. However, traditional dynamic Voronoi diagram methods employ a fixed time-step update strategy that cannot adapt quickly to rapid changes in the fire area. This is particularly true in the face of emergencies such as fire boundary expansion, splitting, merging, or drone damage. Furthermore, such update strategies may miss critical events. For example, if drone A is assigned to monitor area P1, and the fire spreads to area P2, drone A may not be able to cover the new boundary in time. If drone B is damaged, a gap in the original area will appear, resulting in mission failure. Consequently, the system lacks both adaptability and survivability.
[0003] To solve the above problems, the present invention proposes a UAV cluster fire monitoring method based on dynamic Voronoi diagram, which achieves complete coverage of fire scene boundaries, Voronoi diagram reconstruction and coordinated control of UAV cluster. Summary of the Invention
[0004] The purpose of this invention is to improve the UAV cluster fire monitoring method to solve the problems of dynamic spread of fire boundaries, weak cluster anti-destruction ability, and difficulty in balancing coverage range and coverage quality in cluster fire monitoring tasks.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: A method for monitoring fires by drone clusters based on a dynamic Voronoi diagram, the method comprising: S100, obtain the initial information of the fire area, perform equal-space sampling and temperature gradient maximum point sampling on the fire area, and form a local generation point set , the initial deployment point of the drone is arranged according to the location of the initial generation point , and construct the Voronoi cells of the spatial region ; S200, real-time monitoring of various fire events , including fire boundary expansion, fire area merging and splitting, and UAV node damage; through cluster head real-time perception and event judgment, once an event is detected The occurrence of the local generating point set and the corresponding Voronoi cell Update operation; S300, based on the latest generation point set The affected area is locally redivided to form a new Voronoi cell layout. Based on the updated generation point locations, the drones autonomously plan paths and head to the corresponding areas to perform monitoring tasks, achieving local adaptive optimization of regional coverage. S400. After each local reconstruction of the Voronoi diagram, each UAV dynamically adjusts its flight altitude according to the fire intensity distribution and coverage quality function within the Voronoi cell to maximize the local weighted coverage quality.
[0006] Preferably, S100 includes: S101. Based on the initial information of the fire area, the system combines the equal-space sampling and the sampling of the maximum temperature gradient point to obtain the initial generation point set. ; Then the initial deployment point of the drone is arranged according to the location of the generation point, which is recorded as: ; in, Indicates that the system obtains the first location information; Indicates the initial position and height of the drone in three-dimensional space Can be adjusted dynamically later; S102: Constructing Voronoi partitioning units of the spatial region based on the generated point set ; Each Voronoi cell Compatible drones , forming the initial coverage deployment structure.
[0007] Preferably, in S200, real-time perception and event determination are performed by a cluster head, including: Using the clustering method, the cluster is divided into multiple subclusters. Centralized computing is used within each subcluster, and global consistency is achieved through distributed coordination between subclusters. Specifically, each sub-cluster selects a cluster head, which is responsible for centrally calculating the Voronoi partitioning within the sub-cluster; ordinary drones within the sub-cluster are responsible for reporting location information to the cluster head and receiving local Voronoi cells; In order to achieve the integrity of the global Voronoi diagram, each sub-cluster must include the boundary drones of adjacent sub-clusters in addition to the core members when dividing. The influence of the boundary drones of adjacent sub-clusters is considered during calculation. After calculation, only the core members of the sub-cluster are retained and the neighbor drones are ignored.
[0008] Preferably, once an event is detected in S200 The occurrence of the local generating point set and the corresponding Voronoi cell Update operations include: S201. Set the fire area as a two-dimensional plane , the initial generation point set Each point Corresponding to a drone, the Voronoi unit Defined as: ; At this time, the drone will generate Corresponding Perform task allocation and path planning. Under static conditions, if the generated point If all are within the fire boundary, the drone cluster can achieve complete coverage and monitoring of the fire boundary; S202, when the boundary of the fire area As time goes by, the fire spreads outwards. If the fire spreads to the original Voronoi division area If the fire is outside the range of the current UAV, it means that the current UAV mission area can no longer cover the entire fire boundary. At this time, the system will move the generation point , and reconstruct the Voronoi partitioning structure accordingly; S203, when two adjacent fire areas and The boundaries gradually touch and merge into a connected fire area When the system converts the original two Voronoi task units and Merge into a unified sub-region , and reduce one generation point accordingly; if the original fire scene Divided into two disconnected subregions and , the system adds one or more spawn points; S204, in the fire monitoring task, when the system detects a drone When the drone is offline or can no longer perform monitoring tasks, it will be considered damaged. At this time, the corresponding spawn point of the drone The removal creates a coverage hole, and the surrounding generation points move toward the hole area, realizing the natural expansion of the Voronoi unit. If the expansion reaches the limit and still cannot completely cover the hole area, a new generation point is generated and redundant drones are dispatched to cover it.
[0009] Preferably, S400 includes: Set up each drone With adjustable height , the coverage quality of each UAV node is a function ,in The value of is positively correlated with the coverage quality; ; in, Indicates drone Effective sensing range; For each point in the monitored area , with fire intensity , the overall coverage goal is to maximize the weighted coverage quality: .
[0010] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for unmanned aerial vehicle cluster fire monitoring based on a dynamic Voronoi diagram.
[0011] A computer device includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the program, the steps of the above-mentioned unmanned aerial vehicle cluster fire monitoring method based on dynamic Voronoi diagram are implemented.
[0012] Compared with the prior art, the present invention has the following beneficial effects: The present invention introduces a dynamic Voronoi diagram into the drone cluster control system, and achieves continuous tracking and coverage of the fire boundary through generation point guidance; an event-driven update mechanism is introduced to trigger local reconstruction only when key events such as fire boundary expansion, regional splitting and merging, or drone failure occur, thereby effectively improving response efficiency.
[0013] By using an event-driven dynamic Voronoi diagram construction method to adaptively delineate fire boundaries and guide drone clusters to achieve dynamic coverage, real-time monitoring of the fire area is facilitated. Triggered by events such as changes in fire boundaries or node failures, the system locally reconstructs the Voronoi diagram structure and adjusts the mission areas of relevant drones, enabling rapid response to emergencies. Combined with a redundant drone scheduling mechanism, if individual drones are damaged, other nodes within their subcluster can take over the task, ensuring continuous and stable monitoring of the entire monitoring mission and effectively enhancing the system's resilience. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 is the fire boundary Voronoi partition diagram of the present invention; Figure 2 is the Voronoi local reconstruction map of a single affected point of the present invention; Figure 3 It is the Voronoi local reconstruction diagram of the two affected points of the present invention. DETAILED DESCRIPTION
[0015] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0016] See also Figure 1-Figure 3 , the present invention provides a technical solution: Example 1: Traditional drone swarm fire monitoring based on Voronoi diagrams first calculates a static Voronoi diagram offline based on the number of drones, then assigns each drone to its own monitoring cell. This offline calculation and use of static Voronoi diagrams ignore the complexity of fire environments. For example, if drone A is assigned to monitor area P1, and the fire spreads to area P2, drone A may not be able to cover the new boundary in time. If drone B is destroyed, the original area will be left without monitoring, resulting in mission failure. Consequently, the system lacks adaptability and resilience.
[0017] To address these issues, this paper proposes a drone swarm fire monitoring method based on a dynamic Voronoi diagram. This method allows the drone swarm to fully cover the fire boundary and adaptively adjusts its coverage strategy as the fire spreads or drones are damaged, improving the swarm's resilience. Furthermore, formulas for coverage range and coverage quality are introduced, and by combining the dynamic Voronoi diagram with drone altitude adjustment, a balance between coverage range and coverage quality can be achieved.
[0018] The dynamic Voronoi diagram algorithm adapts the Voronoi diagram to changing conditions, making it suitable for delineating fire boundaries. In a static environment, when the drone overlaps with all the generated points on the fire boundary, the fire boundary is completely covered. As the fire boundary changes, the generated points also change. By keeping the drone aligned with the generated points, the fire boundary is consistently and completely covered.
[0019] Specifically, a UAV cluster fire monitoring method based on a dynamic Voronoi diagram includes: S100, obtain the initial information of the fire area, perform equal-space sampling and temperature gradient maximum point sampling on the fire area, and form a local generation point set , the initial deployment point of the drone is arranged according to the location of the initial generation point , and construct the Voronoi cells of the spatial region ; Preferably, S100 includes: S101. Based on the initial information of the fire area, the system combines the equal-space sampling and the sampling of the maximum temperature gradient point to obtain the initial generation point set. ; Then the initial deployment point of the drone is arranged according to the location of the generation point, which is recorded as: ; in, Indicates that the system obtains the first location information; Indicates the initial position and height of the drone in three-dimensional space Can be adjusted dynamically later; S102: Constructing Voronoi partitioning units of the spatial region based on the generated point set ; Each Voronoi cell Compatible drones , forming the initial coverage deployment structure.
[0020] S200, real-time monitoring of various fire events , including fire boundary expansion, fire area merging and splitting, and UAV node damage; through cluster head real-time perception and event judgment, once an event is detected The occurrence of the local generating point set and the corresponding Voronoi cell Update operation; In this paper, we consider using an event-driven update approach to reconstruct the Voronoi diagram. Reconstructing the corresponding local area only occurs when a key event is triggered. This reduces computational costs while ensuring that key events are not missed. This makes the dynamic Voronoi diagram more consistent with fire scenarios, improving the feasibility and accuracy of the algorithm.
[0021] Preferably, the triggering conditions and update strategies are: In an event-driven system, the trigger condition is a specific event generated based on the change of system state.
[0022] S201. Set the fire area as a two-dimensional plane , the initial generation point set Each point Corresponding to a drone, the Voronoi unit Defined as: ; At this time, the drone will generate Corresponding Perform task allocation and path planning. Under static conditions, if the generated point If all the fire areas are within the fire boundary, the drone cluster can achieve complete coverage and monitoring of the fire boundary. The following describes the triggering conditions and update strategies in detail through three typical events: fire boundary expansion, fire area merging or splitting, and drone damage.
[0023] S202, Fire Boundary Expansion: When the boundary of the fire area As time goes by, the fire spreads outwards. If the fire spreads to the original Voronoi division area If the fire is outside the range of the current UAV, it means that the current UAV mission area can no longer cover the entire fire boundary. At this time, the system will move the generation point , and reconstruct the Voronoi partitioning structure accordingly; S203. Fire area merger or split: In some cases, multiple independent fire sources may merge or split due to wind influence or changes in combustion path.
[0024] When two adjacent fire areas and The boundaries gradually touch and merge into a connected fire area When the system converts the original two Voronoi task units and Merge into a unified sub-region , and one generation point is reduced accordingly; if the fire in a certain area is split due to changes in wind speed or terrain, such as the original fire scene Divided into two disconnected subregions and , the system adds one or more spawn points; S204. Drone damage: During fire monitoring missions, some drones may be interrupted due to reasons such as high temperature, airflow interference or hardware failure.
[0025] When the system detects a drone When the drone is offline or can no longer perform monitoring tasks, it will be considered damaged. At this time, the corresponding spawn point of the drone The removal creates a coverage hole, and the surrounding generation points move toward the hole area, realizing the natural expansion of the Voronoi unit. If the expansion reaches the limit and still cannot completely cover the hole area, a new generation point is generated and redundant drones are dispatched to cover it.
[0026] Preferably, in S200, real-time perception and event determination are performed by a cluster head, including: Using the clustering method, the cluster is divided into multiple subclusters. Centralized computing is used within each subcluster, and global consistency is achieved through distributed coordination between subclusters. Specifically, each sub-cluster selects a cluster head, which is responsible for centrally calculating the Voronoi partitioning within the sub-cluster; ordinary drones within the sub-cluster are responsible for reporting location information to the cluster head and receiving local Voronoi cells; In order to achieve the integrity of the global Voronoi diagram, each sub-cluster must include the boundary drones of adjacent sub-clusters in addition to the core members when dividing. The influence of the boundary drones of adjacent sub-clusters is considered during calculation. After calculation, only the core members of the sub-cluster are retained and the neighbor drones are ignored.
[0027] S300, based on the latest generation point set The affected area is locally redivided to form a new Voronoi cell layout. Based on the updated generation point locations, the drones autonomously plan paths and head to the corresponding areas to perform monitoring tasks, achieving local adaptive optimization of regional coverage. S400. After each local reconstruction of the Voronoi diagram, each UAV dynamically adjusts its flight altitude according to the fire intensity distribution and coverage quality function within the Voronoi cell to maximize the local weighted coverage quality.
[0028] Preferably, S400 includes: Setting up each drone With adjustable height , the coverage quality of each UAV node is a function ,in The value of is positively correlated with the coverage quality; ; in, Indicates drone Effective sensing range; For each point in the monitored area , with fire intensity , the overall coverage goal is to maximize the weighted coverage quality: .
[0029] Preferably, Figure 1A Voronoi partition diagram of the fire boundary is shown. The red curve represents the irregular fire boundary, the dots are the generation points of the Voronoi partition diagram, and the blue solid and dashed lines represent the Voronoi cell divisions. Accurately understanding the fire spread trend is crucial during fire monitoring. Therefore, when performing fire boundary monitoring tasks, a drone swarm needs to dispatch drones according to the generation points shown in the diagram and determine the minimum coverage height for each drone based on the corresponding Voronoi cell divisions. Because the fire boundary is divided into multiple Voronoi cells, each corresponding to a generation point, full coverage of the fire boundary is achieved when the altitudes of all drones meet their respective minimum altitude requirements. This altitude is then used as the minimum standard for balancing coverage range and coverage quality. Combined with relevant formulas, an optimal altitude can be calculated, which achieves the optimal balance between coverage range and quality while ensuring complete coverage of the fire boundary.
[0030] Figure 2 and Figure 3 The following figures show local Voronoi reconstructions for a single affected point and two affected points, respectively. In these figures, blue dots represent the initial generation points, and orange dots represent newly generated points affected by fire spread. Disturbance here refers to updates caused by events such as fire spread, which result in changes in the positions of the generation points. The blue lines represent the Voronoi partitioning formed based on the initial generation points, while the green lines represent the Voronoi partitioning formed based on the perturbed generation points. Because these updates are local, the blue and green lines differ only within the neighborhood of the perturbed point; the rest of the area remains the same. During fire boundary monitoring, fire boundaries change in real time. Therefore, using a Voronoi diagram to delineate fire boundaries requires continuous updating of the Voronoi diagram. This invention utilizes a dynamic Voronoi diagram method based on event-driven updates, triggering local updates only when key events occur. This effectively reduces computational costs and ensures timely response to key events. By designing trigger strategies for key events such as drone damage, the system's survivability is enhanced. Furthermore, by precisely determining the minimum altitude and final altitude selection for each drone, a balance between coverage range and coverage quality is achieved.
[0031] Example 2: The computer-readable storage medium of this embodiment stores a computer program, which, when executed by a processor, implements the steps of a method for drone cluster fire monitoring based on a dynamic Voronoi diagram in Example 1.
[0032] The computer-readable storage medium of this embodiment may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal; the computer-readable storage medium of this embodiment may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, etc. equipped on the terminal; further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device.
[0033] The computer-readable storage medium of this embodiment is used to store computer programs and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or is to be output.
[0034] Example 3: The computer device of this embodiment includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the method for drone cluster fire monitoring based on dynamic Voronoi diagram in Example 1 are implemented.
[0035] In this embodiment, the processor can be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The memory can include read-only memory and random access memory, and provide instructions and data to the processor. A part of the memory can also include non-volatile random access memory. For example, the memory can also store information about the device type.
[0036] Those skilled in the art will appreciate that the disclosed embodiments may be provided as methods, systems, or computer program products. Therefore, the present solution may take the form of a hardware embodiment, a software embodiment, or a combination of software and hardware embodiments. Furthermore, the present solution may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage) containing computer-usable program code.
[0037] The present solution is described with reference to the flowcharts and / or block diagrams of the methods and computer program products according to the embodiments of the present solution. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as the combination of the processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions; these computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the flowcharts and / or block diagrams. Figure 1a process or multiple processes and / or methods Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0038] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or methods Figure 1 The function specified in one or more boxes.
[0039] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or methods Figure 1 A step that specifies a function in one or more boxes.
[0040] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).
[0041] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.
Claims
1. A method for fire monitoring using a drone cluster based on a dynamic Voronoi diagram, characterized by: The method comprises: S100, obtain the initial information of the fire area, perform equal-space sampling and temperature gradient maximum point sampling on the fire area, and form a local generation point set , the initial deployment point of the drone is arranged according to the location of the initial generation point , and construct the Voronoi cells of the spatial region ; S200, real-time monitoring of various fire events , including fire boundary expansion, fire area merging and splitting, and UAV node damage; through cluster head real-time perception and event judgment, once an event is detected The occurrence of the local generating point set and the corresponding Voronoi cell Update operation; S300, based on the latest generation point set The affected area is locally redivided to form a new Voronoi cell layout. Based on the updated generation point locations, the drones autonomously plan paths and head to the corresponding areas to perform monitoring tasks, achieving local adaptive optimization of regional coverage. S400. After each local reconstruction of the Voronoi diagram, each UAV dynamically adjusts its flight altitude according to the fire intensity distribution and coverage quality function within the Voronoi cell to maximize the local weighted coverage quality.
2. The method for fire monitoring of drone clusters based on dynamic Voronoi diagram according to claim 1, characterized in that: The S100 includes: S101. Based on the initial information of the fire area, the system combines the equal-space sampling and the sampling of the maximum temperature gradient point to obtain the initial generation point set. ; Then the initial deployment point of the drone is arranged according to the location of the generation point, which is recorded as: ; in, Indicates that the system obtains the first location information; Indicates the initial position and height of the drone in three-dimensional space Can be adjusted dynamically later; S102: Constructing Voronoi partitioning units of the spatial region based on the generated point set ; Each Voronoi cell Compatible drones , forming the initial coverage deployment structure.
3. The method for fire monitoring of drone clusters based on dynamic Voronoi diagram according to claim 1, characterized in that: The real-time perception and event determination in S200 are performed by the cluster head, including: Using the clustering method, the cluster is divided into multiple subclusters. Centralized computing is used within each subcluster, and global consistency is achieved through distributed coordination between subclusters. Specifically, each sub-cluster selects a cluster head, which is responsible for centrally calculating the Voronoi partitioning within the sub-cluster; ordinary drones within the sub-cluster are responsible for reporting location information to the cluster head and receiving local Voronoi cells; In order to achieve the integrity of the global Voronoi diagram, each sub-cluster must include the boundary drones of adjacent sub-clusters in addition to the core members when dividing. The influence of the boundary drones of adjacent sub-clusters is considered during calculation. After calculation, only the core members of the sub-cluster are retained and the neighbor drones are ignored.
4. The method for fire monitoring of drone clusters based on dynamic Voronoi diagram according to claim 1, characterized in that: Once an event is detected in S200 The occurrence of the local generating point set and the corresponding Voronoi cell Update operations include: S201. Set the fire area as a two-dimensional plane , the initial generation point set Each point Corresponding to a drone, the Voronoi unit Defined as: ; At this time, the drone will generate Corresponding Perform task allocation and path planning. Under static conditions, if the generated point If all are within the fire boundary, the drone cluster can achieve complete coverage and monitoring of the fire boundary; S202, when the boundary of the fire area As time goes by, the fire spreads outwards. If the fire spreads to the original Voronoi division area If the UAV's mission area cannot cover the entire fire boundary, the system will move the spawn point. , and reconstruct the Voronoi partitioning structure accordingly; S203, when two adjacent fire areas and The boundaries gradually touch and merge into a connected fire area When the system converts the original two Voronoi task units and Merge into a unified sub-region , and reduce one generation point accordingly; if the original fire scene Divided into two disconnected subregions and , the system adds one or more spawn points; S204, in the fire monitoring task, when the system detects a drone When the drone is offline or can no longer perform monitoring tasks, it will be considered damaged. At this time, the corresponding spawn point of the drone The removal creates a coverage hole, and the surrounding generation points move toward the hole area, realizing the natural expansion of the Voronoi unit. If the expansion reaches the limit and still cannot completely cover the hole area, a new generation point is generated and redundant drones are dispatched to cover it.
5. The method for fire monitoring of drone clusters based on dynamic Voronoi diagram according to claim 1, characterized in that: The S400 includes: Setting up each drone With adjustable height , the coverage quality of each UAV node is a function ,in The value of is positively correlated with the coverage quality; ； in, Indicates drone Effective sensing range; For each point in the monitored area , with fire intensity , the overall coverage goal is to maximize the weighted coverage quality: 。 6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of a UAV cluster fire monitoring method based on a dynamic Voronoi diagram as described in any one of claims 1 to 5 are implemented.
7. A computer device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of the UAV cluster fire monitoring method based on dynamic Voronoi diagram according to any one of claims 1 to 5 are implemented.