High-order distributed fire-fighting unmanned aerial vehicle task allocation method and system

Abstract

The invention provides a high-order distributed fire-fighting unmanned aerial vehicle task allocation method and system, and relates to the technical field of unmanned aerial vehicle task allocation, and the method comprises the following steps: obtaining a thermal infrared image and necessary parameters; calculating the length and width of a thermal infrared image coverage area corresponding to a single pixel point; converting the thermal infrared image into a grey-scale map, carrying out binarization processing on the fire area, and calculating the area of the fire area; extracting a fire area boundary, establishing a local coordinate system, and calculating coordinates of the fire area boundary and the fire-fighting unmanned aerial vehicle; and carrying out distributed collaborative decision and task allocation. The method has the beneficial effects that the single-point fault problem in a centralized mode is avoided, the system reliability and robustness are high, the information interaction and cooperation are efficient, the decision process is simplified, the task repeated allocation is avoided, and the allocation strategy can be adjusted according to the dynamic change of the fire area.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle task allocation, and in particular to a high-order distributed firefighting unmanned aerial vehicle task allocation method and system. Background Art

[0002] With the deep penetration of drone technology in the firefighting field, the task allocation technology of firefighting drones has become a key research direction to improve the efficiency of fire fighting. In recent years, this field has carried out research on multi-drone collaborative path planning and task scheduling algorithms, integrating geographic information systems, intelligent optimization algorithms, etc., and is committed to optimizing drone resource allocation. Related technologies have made progress in single-machine task execution and simple scene scheduling, but in the face of distributed collaboration needs in complex fire environments, the existing technology system still needs to be further improved.

[0003] First, existing technologies mostly adopt a centralized task allocation architecture, relying on central nodes for information processing and decision-making. However, in firefighting scenarios, central nodes are susceptible to fire damage or communication interference. Once they fail, the system will crash, making it difficult to ensure robustness and unable to adapt to the complex communication environment of the fire scene. Secondly, due to the lack of an efficient distributed information interaction mechanism, it is difficult for multiple drones to achieve consistent convergence of global information under local communication conditions, resulting in a lack of accurate understanding of the overall situation of the fire scene in task allocation, and the scientific nature of decision-making is limited. Finally, existing technologies mostly focus on task allocation based on static fire area information, ignoring the real-time relationship between drones and fire boundaries, as well as possible competition and conflict when multiple drones collaborate.

[0004] How to solve the above technical problems is the subject faced by the present invention. Summary of the invention

[0005] In order to address the shortcomings of the prior art, the present invention provides a high-order distributed firefighting drone system task allocation method that avoids the single point failure problem in the centralized mode, has high system reliability and robustness, efficient information interaction and collaboration, simplifies the decision-making process, avoids repeated task allocation, and can adjust the allocation strategy according to the dynamic changes of the fire area.

[0006] The technical solution adopted by the present invention to solve the technical problem is: the present invention provides a high-order distributed firefighting UAV task allocation method, comprising the following steps: Acquire thermal infrared images and necessary parameters.

[0007] Calculate the length and width of the thermal infrared image coverage area corresponding to a single pixel.

[0008] The thermal infrared image is converted into a grayscale image, the fire area is binarized, and the area of ​​the fire area is calculated.

[0009] The fire area boundary is extracted, a local coordinate system is established, and the coordinates of the fire area boundary and the firefighting drone are calculated.

[0010] Distributed collaborative decision making and task allocation.

[0011] Preferably, the acquisition of thermal infrared images and necessary parameters are specifically: Use thermal infrared imaging drones to vertically shoot the fire scene to obtain high-precision thermal infrared images and flight altitude H and horizontal field of view angle , vertical field of view , the number of pixels in the horizontal direction of the image , the number of pixels in the vertical direction of the image , the longitude of the infrared imaging drone , the latitude of the infrared imaging drone , Firefighting drone latitude and longitude collection ,in .

[0012] It should be noted that the thermal infrared image is obtained by vertical shooting by a thermal infrared imaging drone, and the field of view is evenly distributed. The horizontal viewing angle corresponds to the longitude direction of the geographical location, and the vertical viewing angle corresponds to the latitude direction of the geographical location. Therefore, the image increases from left to right in the direction of increasing longitude, and from bottom to top in the direction of increasing latitude.

[0013] Preferably, the length and width of the thermal infrared image coverage area corresponding to a single pixel point are calculated as follows: According to the collected flight altitude H, horizontal field of view and vertical field of view Information, use the tangent function to calculate the length X and width Y of the area covered by the thermal infrared image; The length X of the area covered by the thermal infrared image and the number of pixels in the horizontal direction of the image are used respectively The ratio of the width Y of the thermal infrared image coverage area to the number of pixels in the vertical direction of the image The ratio of the length of the thermal infrared image coverage area corresponding to a single pixel is calculated and width .

[0014] The relationship expression of the actual coverage area of ​​the thermal infrared image is as follows: ; The length and width of the thermal infrared image coverage area corresponding to a single pixel are expressed as follows: ; It should be noted that when the thermal infrared imaging drone shoots vertically, its field of view (horizontal viewing angle) , vertical viewing angle ) forms a coverage area similar to a "conical projection". The flight altitude H is used as the vertical axis and together with the field of view angle determines the size of the actual coverage area on the ground.

[0015] For the horizontal direction, half of the horizontal field of view As the angle, the flight height H is used as the right angle side, and the half length of the ground coverage area is calculated using the tangent function, that is, , and multiply by 2 to get the full length.

[0016] Similarly, the vertical direction is half of the vertical field of view. is the angle, and the half-width is calculated by the tangent function , multiply by 2 to get the width.

[0017] Preferably, the thermal infrared image is loaded and converted into a grayscale image, the fire area is binarized, a fixed threshold m is used, the area above the fixed threshold m is marked as white, and the rest of the area is marked as black, a binary mask of the fire scene is generated, and the number of pixels in the white area is counted. , combined with the length of the area covered by the thermal infrared image corresponding to a single pixel and width Calculate the area of ​​the fire zone.

[0018] The fire zone area calculation formula is as follows: ; Represents the actual geographical length of the area covered by the thermal infrared image corresponding to a single pixel. It represents the actual geographical width of the area covered by the thermal infrared image corresponding to a single pixel. The product of the two represents the actual geographical area covered by a single pixel. The area of ​​the fire area = the total number of pixels in the fire area × the actual geographical area covered by a single pixel.

[0019] Preferably, the extraction of the fire area boundary, establishment of the local coordinate system, and calculation of the fire area boundary and the coordinates of the firefighting drone are specifically as follows: Use the contour search algorithm to extract the fire area boundary from the binary image and obtain the pixel coordinate set of the fire area boundary ,in .

[0020] Use the thermal infrared imaging drone shooting location as the origin , establish a local coordinate system, in which the increasing direction of the x-axis is consistent with the increasing direction of the longitude, and the increasing direction of the y-axis is consistent with the increasing direction of the latitude.

[0021] According to the pixel coordinates of the fire area boundary Relative to the center of the image The offset of the thermal infrared image is combined with the length of the area covered by the thermal infrared image corresponding to a single pixel. and width , calculate the coordinates of the fire area boundary in the local coordinate system, the coordinate set of the pixel points on the fire area boundary in the local coordinate system , where the coordinates of the i-th pixel point on the fire area boundary in the local coordinate system are The calculation is as follows: ; It should be noted that the image pixel coordinates usually take the upper left corner as the origin (x to the right, y to the bottom), while the local coordinate system takes the position of the thermal infrared imaging drone as the origin (x corresponds to the direction of increasing longitude, y corresponds to the direction of increasing latitude). Therefore, when calculating the ordinate, it is necessary to add a minus sign to reverse the y-axis direction of the image pixel coordinate system to make it consistent with the local coordinate system.

[0022] According to the latitude and longitude coordinates of the firefighting drone Relative to the longitude and latitude coordinates of the thermal infrared imaging drone The offset of the firefighting drone is combined with the actual distance corresponding to a 1° difference in longitude and latitude to calculate the coordinates of the firefighting drone in the local coordinate system. The calculation formula is as follows: ; It should be noted that 111320 is the approximate distance (in meters) corresponding to a 1° difference in longitude and latitude. Taking into account the different actual distances corresponding to a 1° difference in longitude at different latitudes, correction is made by taking the cosine value of the average of the two latitudes.

[0023] Preferably, the distributed collaborative decision-making and task allocation are specifically: Several firefighting UAVs are taken as nodes. Combined with the communication situation between firefighting UAVs, UAV auxiliary state variables and filter adjustment parameters are introduced to construct a distributed average consistency filter. Through the distributed average consistency filter, each UAV only relies on local communication (neighbor node information) and gradually achieves consistent convergence of global information, ensuring that the system can stably share key data in a dynamic communication environment.

[0024] The distributed average consistency filter expression is as follows: ; In the formula, Indicates whether the i-th firefighting drone can receive the communication of the j-th firefighting drone. 0 means that it cannot receive the communication, and 1 means that it can receive the communication. for Valuation of is the auxiliary state variable of the i-th UAV, used to propagate global average information; is the adjustment parameter of the filter.

[0025] It should be noted that Influences on the convergence speed of the distributed average consistency filter. In practical applications, numerical simulation can be used to test different The convergence performance under value.

[0026] exist middle, Determines the communication relationship, Represents the difference between the auxiliary state variables of the neighboring drone and itself and the local information The combined effect of In order to make the estimated value Over time, all drones It will gradually converge to the global average information.

[0027] exist In the example, the auxiliary state variables of the ith UAV are The rate of change depends on its relationship with neighboring drones. If the neighboring drone’s estimate is different from its own, then will change, thereby promoting the spread of information between adjacent drones.

[0028] A winner-takes-all competition strategy model is established. The distance between the firefighting drone and the nearest vertex of the fire scene, the communication status between drones, and the activation status of drones are used as model inputs. Combined with the size of the fire area, the winner-takes-all competition strategy model allocates tasks to the firefighting drones. The winner-takes-all competition strategy model is as follows: ; In the formula, is the activation state of the i-th firefighting drone, if It means it is activated and the i-th firefighting drone is dispatched to perform the mission. It means it is not activated; It is the adjustment parameter of the evolution speed of the winner-takes-all competition strategy model; is the distance between the ith firefighting drone and the nearest vertex of the fire scene, ; It is the adjustment parameter related to the fire area in the winner-takes-all competition strategy model; An offset parameter related to the fire area in the winner-take-all competition strategy model to avoid the situation where the denominator is zero; is the area of ​​the fire zone; where, Indicates whether the p-th firefighting drone can receive the communication from the q-th firefighting drone. 0 means it cannot receive the communication, and 1 means it can receive the communication.

[0029] It should be noted that the parameters of the model are given based on numerical simulation tests combined with the experience of technicians.

[0030] Each firefighting drone participates in the competition based on the distance from the nearest vertex of the fire scene and the area of ​​the fire area. The smaller the distance from the nearest vertex of the fire scene, the easier it is to be activated. The larger the area of ​​the fire area, the more firefighting drones may be activated.

[0031] , the activation status of adjacent drones is taken into account. If the adjacent drone has been activated, it will affect the activation status of the current drone, reflecting the cooperative and competitive relationship between drones.

[0032] is a suppression item, which is used to suppress the excessive activation of the drone. When increasing, The absolute value of ’s growth, ensuring that only a few superior drones are activated in the end, achieving a “winner takes all” effect.

[0033] The present invention also provides a high-order distributed firefighting drone task allocation system, comprising: Data acquisition module, which acquires thermal infrared images and necessary parameters through thermal infrared imaging drones; A calculation module is used to calculate the length and width of the thermal infrared image coverage area corresponding to a single pixel point, the area of ​​the fire area, the coordinates of the fire area boundary, the coordinates of the firefighting drone, and the distance between the firefighting drone and the nearest vertex of the fire area; An image processing module is used to convert the thermal infrared image into a grayscale image, perform binary processing on the fire area, and extract the boundary of the fire area; The task assignment module inputs external data and assigns tasks to firefighting drones based on the distributed average consistency filter and the winner-takes-all competition strategy model.

[0034] The beneficial effects of the present invention are: avoiding the single point failure problem in the centralized mode, high system reliability and robustness, efficient information interaction and collaboration, simplifying the decision-making process, avoiding repeated task allocation, and being able to adjust the allocation strategy according to the dynamic changes of the fire area. By introducing a distributed task allocation mechanism, the single point failure problem in the centralized mode is avoided. Each drone makes independent decisions based on local information and feedback from neighboring drones, thereby improving the reliability and fault tolerance of the system; by adopting a task allocation method based on a winner-takes-all competition strategy model, each drone competes according to its own position and the size of the fire area, and drones closer to the fire are given priority to perform tasks. The larger the fire area, the more drones are dispatched. This method simplifies the decision-making process and avoids repeated task allocation. By constructing a high-order network, the present invention strengthens information sharing and collaboration between drones, making task allocation more intelligent and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a diagram of the method steps of the present invention.

[0036] Figure 2 It is a system module diagram of the present invention.

[0037] Figure 3 In Example 3 of the present invention, when the fire area is 90 square meters Schematic diagram of the change process.

[0038] Figure 4 When the fire area in Example 3 of the present invention is 350 square meters Schematic diagram of the change process. DETAILED DESCRIPTION

[0039] In order to clearly illustrate the technical features of this solution, this solution is described below through specific implementation methods.

[0040] Example 1: See Figure 1 As shown, this embodiment is a high-order distributed firefighting drone task allocation method, comprising the following steps:

[0041] S1. Obtain thermal infrared images and necessary parameters.

[0042] Use thermal infrared imaging drones to vertically shoot the fire scene to obtain high-precision thermal infrared images and flight altitude H and horizontal field of view angle , vertical field of view , the number of pixels in the horizontal direction of the image , the number of pixels in the vertical direction of the image , the longitude of the infrared imaging drone , the latitude of the infrared imaging drone , Firefighting drone latitude and longitude collection ,in .

[0043] It should be noted that the thermal infrared image is obtained by vertical shooting by a thermal infrared imaging drone, and the field of view is evenly distributed. The horizontal viewing angle corresponds to the longitude direction of the geographical location, and the vertical viewing angle corresponds to the latitude direction of the geographical location. Therefore, the image increases from left to right in the direction of increasing longitude, and from bottom to top in the direction of increasing latitude.

[0044] S2. Calculate the length and width of the thermal infrared image coverage area corresponding to a single pixel.

[0045] According to the collected flight altitude H, horizontal field of view and vertical field of view Information, use the tangent function to calculate the length X and width Y of the area covered by the thermal infrared image; The length X of the area covered by the thermal infrared image and the number of pixels in the horizontal direction of the image are used respectively The ratio of the width Y of the thermal infrared image coverage area to the number of pixels in the vertical direction of the image The ratio of the length of the thermal infrared image coverage area corresponding to a single pixel is calculated and width .

[0046] The relationship expression of the actual coverage area of ​​the thermal infrared image is as follows: ; The length and width of the thermal infrared image coverage area corresponding to a single pixel are expressed as follows: ; It should be noted that when the thermal infrared imaging drone shoots vertically, its field of view (horizontal viewing angle) , vertical viewing angle ) forms a coverage area similar to a "conical projection". The flight altitude H is used as the vertical axis and together with the field of view angle determines the size of the actual coverage area on the ground.

[0047] For the horizontal direction, half of the horizontal field of view As the included angle, the flight height H is used as the right angle side, and the half length of the ground coverage area is calculated using the tangent function, that is, , and multiply by 2 to get the full length.

[0048] Similarly, the vertical direction is half of the vertical field of view. is the angle, and the half-width is calculated by the tangent function , multiply by 2 to get the width.

[0049] S3. Convert the thermal infrared image into a grayscale image, perform binarization on the fire area, and calculate the area of ​​the fire area.

[0050] Load the thermal infrared image and convert it to grayscale. Binarize the fire area. Use a fixed threshold m to mark the area above the fixed threshold m as white and the rest as black. Generate a binary mask of the fire scene and count the number of pixels in the white area. , combined with the length of the area covered by the thermal infrared image corresponding to a single pixel and width Calculate the area of ​​the fire zone.

[0051] The fire zone area calculation formula is as follows: ; Represents the actual geographical length of the area covered by the thermal infrared image corresponding to a single pixel. It represents the actual geographical width of the area covered by the thermal infrared image corresponding to a single pixel. The product of the two represents the actual geographical area covered by a single pixel. The area of ​​the fire area = the total number of pixels in the fire area × the actual geographical area covered by a single pixel.

[0052] S4. Extract the fire area boundary, establish a local coordinate system, and calculate the coordinates of the fire area boundary and the firefighting drone.

[0053] Use the contour search algorithm to extract the fire area boundary from the binary image and obtain the pixel coordinate set of the fire area boundary ,in .

[0054] Use the thermal infrared imaging drone shooting location as the origin , establish a local coordinate system, in which the increasing direction of the x-axis is consistent with the increasing direction of the longitude, and the increasing direction of the y-axis is consistent with the increasing direction of the latitude.

[0055] According to the pixel coordinates of the fire area boundary Relative to the center of the image The offset of the thermal infrared image is combined with the length of the area covered by the thermal infrared image corresponding to a single pixel. and width , calculate the coordinates of the fire area boundary in the local coordinate system, the coordinate set of the pixel points on the fire area boundary in the local coordinate system , where the coordinates of the i-th pixel point on the fire area boundary in the local coordinate system are The calculation is as follows: ; It should be noted that the image pixel coordinates usually take the upper left corner as the origin (x to the right, y to the bottom), while the local coordinate system takes the position of the thermal infrared imaging drone as the origin (x corresponds to the direction of increasing longitude, y corresponds to the direction of increasing latitude). Therefore, when calculating the ordinate, it is necessary to add a minus sign to reverse the y-axis direction of the image pixel coordinate system to make it consistent with the local coordinate system.

[0056] According to the latitude and longitude coordinates of the firefighting drone Relative to the longitude and latitude coordinates of the thermal infrared imaging drone The offset of the firefighting drone is combined with the actual distance corresponding to a 1° difference in longitude and latitude to calculate the coordinates of the firefighting drone in the local coordinate system. The calculation formula is as follows: ; It should be noted that 111320 is the approximate distance (in meters) corresponding to a 1° difference in longitude and latitude. Taking into account the different actual distances corresponding to a 1° difference in longitude at different latitudes, correction is made by taking the cosine value of the average of the two latitudes.

[0057] S5. Distributed collaborative decision-making and task allocation.

[0058] Several firefighting UAVs are taken as nodes. Combined with the communication situation between firefighting UAVs, UAV auxiliary state variables and filter adjustment parameters are introduced to construct a distributed average consistency filter. Through the distributed average consistency filter, each UAV only relies on local communication (neighbor node information) and gradually achieves consistent convergence of global information, ensuring that the system can stably share key data in a dynamic communication environment.

[0059] The distributed average consistency filter expression is as follows: ; In the formula, Indicates whether the i-th firefighting drone can receive the communication of the j-th firefighting drone. 0 means that it cannot receive the communication, and 1 means that it can receive the communication. for Valuation of is the auxiliary state variable of the i-th UAV, used to propagate global average information; is the adjustment parameter of the filter.

[0060] It should be noted that Influences on the convergence speed of the distributed average consistency filter. In practical applications, numerical simulation can be used to test different The convergence performance under value.

[0061] exist middle, Determines the communication relationship, Represents the difference between the auxiliary state variables of the neighboring drone and itself and the local information The combined effect of In order to make the estimated value Over time, all drones It will gradually converge to the global average information.

[0062] exist In the example, the auxiliary state variables of the ith UAV are The rate of change depends on its relationship with neighboring drones. If the neighboring drone’s estimate is different from its own, then will change, thereby promoting the spread of information between adjacent drones.

[0063] A winner-takes-all competition strategy model is established. The distance between the firefighting drone and the nearest vertex of the fire scene, the communication status between drones, and the activation status of drones are used as model inputs. Combined with the size of the fire area, the winner-takes-all competition strategy model allocates tasks to the firefighting drones. The winner-takes-all competition strategy model is as follows: ; In the formula, is the activation state of the i-th firefighting drone, if It means it is activated and the i-th firefighting drone is dispatched to perform the mission. It means it is not activated; It is the adjustment parameter of the evolution speed of the winner-takes-all competition strategy model; is the distance between the ith firefighting drone and the nearest vertex of the fire scene, ; It is the adjustment parameter related to the fire area in the winner-takes-all competition strategy model; An offset parameter related to the fire area in the winner-take-all competition strategy model to avoid the situation where the denominator is zero; is the area of ​​the fire zone; where, Indicates whether the p-th firefighting drone can receive the communication from the q-th firefighting drone. 0 means it cannot receive the communication, and 1 means it can receive the communication.

[0064] It should be noted that the parameters of the model are given based on numerical simulation tests combined with the experience of technicians.

[0065] Each firefighting drone participates in the competition based on the distance from the nearest vertex of the fire scene and the area of ​​the fire area. The smaller the distance from the nearest vertex of the fire scene, the easier it is to be activated. The larger the area of ​​the fire area, the more firefighting drones may be activated.

[0066] , the activation status of adjacent drones is taken into account. If the adjacent drone has been activated, it will affect the activation status of the current drone, reflecting the cooperative and competitive relationship between drones.

[0067] is a suppression item, which is used to suppress the excessive activation of the drone. When increasing, The absolute value of ’s growth, ensuring that only a few superior drones are activated in the end, achieving a “winner takes all” effect.

[0068] Example 2: See Figure 2 As shown, this embodiment is a high-order distributed firefighting drone task allocation system, including: Data acquisition module, which acquires thermal infrared images and necessary parameters through thermal infrared imaging drones; A calculation module is used to calculate the length and width of the thermal infrared image coverage area corresponding to a single pixel point, the area of ​​the fire area, the coordinates of the fire area boundary, the coordinates of the firefighting drone, and the distance between the firefighting drone and the nearest vertex of the fire area; An image processing module is used to convert the thermal infrared image into a grayscale image, perform binary processing on the fire area, and extract the boundary of the fire area; The task assignment module inputs external data and assigns tasks to firefighting drones based on the distributed average consistency filter and the winner-takes-all competition strategy model.

[0069] Example 3: See Figure 3 , Figure 4 As shown, in order to illustrate the effectiveness of the high-order distributed fire-fighting drone task allocation method proposed in the present invention, this embodiment constructs a high-order distributed network with 10 fire-fighting drones, and performs drone task allocation simulation for the situations where the fire area is 90 square meters and 350 square meters respectively.

[0070] In the two fire area situations, the distributed average consistency filter and the winner-takes-all competition strategy model of this embodiment use the same parameters, and the specific values ​​are as follows: ; ; For the activation status of the i-th drone In this embodiment, the initial value is taken as 0.1, and the relevant values ​​are brought into the distributed average consistency filter and the winner-takes-all competition strategy model for calculation. The activation state is obtained under the two fire area situations. Changes over time, such as Figure 3 , Figure 4 As shown. According to calculation, when the fire area is 90 square meters, , and The value of is greater than 0, the system dispatches the 1st, 4th and 5th firefighting drones to perform the task; when the fire area is 350 square meters, , , , and If the value of is greater than 0, the system dispatches the 1st, 4th, 5th, 6th and 7th firefighting UAVs to perform the mission.

[0071] It can be seen from the above simulation test results that a high-order distributed fire-fighting drone task allocation method provided by the present invention adopts a task allocation method based on a winner-takes-all competition strategy model. Each drone competes according to its own position and the size of the fire area, and drones closer to the fire are preferentially dispatched to perform tasks. The larger the fire area, the more drones are dispatched. This method simplifies the decision-making process, avoids repeated task allocation and single point failure problems in a centralized mode, has high system reliability and robustness, and is efficient in information interaction and collaboration, and can adjust the allocation strategy according to dynamic changes in the fire area.

[0072] Technical features not described in the present invention can be achieved through or by adopting existing technologies and will not be described in detail here. Of course, the above description is not a limitation of the present invention, and the present invention is not limited to the above examples. Changes, modifications, additions or substitutions made by ordinary technicians in this technical field within the essential scope of the present invention should also fall within the scope of protection of the present invention.

Claims

1. A high-order distributed firefighting UAV task allocation method, characterized in that: The following steps are involved: Acquire thermal infrared images and necessary parameters; Calculate the length and width of the thermal infrared image coverage area corresponding to a single pixel; Convert the thermal infrared image into a grayscale image, perform binary processing on the fire area, and calculate the area of ​​the fire area; Extract the fire area boundary, establish a local coordinate system, and calculate the coordinates of the fire area boundary and the firefighting drone; Distributed collaborative decision making and task allocation.

2. The high-order distributed firefighting UAV task allocation method according to claim 1 is characterized in that: The acquisition of thermal infrared images and necessary parameters are specifically: Use thermal infrared imaging drones to vertically shoot the fire scene to obtain high-precision thermal infrared images and flight altitude H and horizontal field of view angle , vertical field of view , the number of pixels in the horizontal direction of the image , the number of pixels in the vertical direction of the image , the longitude of the infrared imaging drone , the latitude of the infrared imaging drone , Firefighting drone latitude and longitude collection ,in .

3. The high-order distributed firefighting UAV task allocation method according to claim 1 is characterized in that: The length and width of the thermal infrared image coverage area corresponding to a single pixel are calculated as follows: According to the collected flight altitude H, horizontal field of view and vertical field of view Information, use the tangent function to calculate the length X and width Y of the area covered by the thermal infrared image; The length X of the area covered by the thermal infrared image and the number of pixels in the horizontal direction of the image are used respectively The ratio of the width Y of the thermal infrared image coverage area to the number of pixels in the vertical direction of the image The ratio of the length of the thermal infrared image coverage area corresponding to a single pixel is calculated and width .

4. The high-order distributed firefighting UAV task allocation method according to claim 1 is characterized in that: The thermal infrared image is converted into a grayscale image, the fire area is binarized, and the area of ​​the fire area is calculated as follows: Load the thermal infrared image and convert it to grayscale. Binarize the fire area. Use a fixed threshold m to mark the area above the fixed threshold m as white and the rest as black. Generate a binary mask of the fire scene and count the number of pixels in the white area. , combined with the length of the area covered by the thermal infrared image corresponding to a single pixel and width Calculate the area of ​​the fire zone.

5. The high-order distributed firefighting UAV task allocation method according to claim 1 is characterized in that: The extraction of the fire area boundary, establishment of the local coordinate system, and calculation of the fire area boundary and the coordinates of the firefighting drone are specifically as follows: Use the contour search algorithm to extract the fire area boundary from the binary image and obtain the pixel coordinate set of the fire area boundary ,in ; Use the thermal infrared imaging drone shooting location as the origin , establish a local coordinate system, wherein the increasing direction of the x-axis of the local coordinate system is consistent with the increasing direction of the longitude, and the increasing direction of the y-axis is consistent with the increasing direction of the latitude; According to the pixel coordinates of the fire area boundary Relative to the center of the image The offset of the thermal infrared image is combined with the length of the area covered by the thermal infrared image corresponding to a single pixel. and width , calculate the coordinates of the fire area boundary in the local coordinate system; According to the latitude and longitude coordinates of the firefighting drone Relative to the longitude and latitude coordinates of the thermal infrared imaging drone The offset is combined with the actual distance corresponding to a 1° difference in longitude and latitude to calculate the coordinates of the firefighting UAV in the local coordinate system.

6. The high-order distributed firefighting UAV task allocation method according to claim 1 is characterized in that: The distributed collaborative decision-making and task allocation are specifically as follows: Several firefighting drones are used as nodes. Combined with the communication between firefighting drones, drone auxiliary state variables and filter adjustment parameters are introduced to construct a distributed average consistency filter. A winner-takes-all competition strategy model is established. The distance between the firefighting UAV and the nearest vertex of the fire scene, the communication status between UAVs and the activation status of UAVs are used as model inputs. Combined with the size of the fire area, the winner-takes-all competition strategy model allocates tasks to the firefighting UAVs.

7. A high-order distributed firefighting drone task allocation system, characterized in that: include: Data acquisition module, which acquires thermal infrared images and necessary parameters through thermal infrared imaging drones; A calculation module is used to calculate the length and width of the thermal infrared image coverage area corresponding to a single pixel point, the area of ​​the fire area, the coordinates of the fire area boundary, the coordinates of the firefighting drone, and the distance between the firefighting drone and the nearest vertex of the fire area; An image processing module is used to convert the thermal infrared image into a grayscale image, perform binary processing on the fire area, and extract the boundary of the fire area; The task assignment module inputs external data and assigns tasks to firefighting drones based on the distributed average consistency filter and the winner-takes-all competition strategy model.

Images