Method and device for calculating endurance duration of low-altitude aircraft and medium

Abstract

The invention discloses a method and equipment for calculating endurance duration of a low-altitude aircraft and a medium. The method comprises the following steps: receiving basic event data corresponding to an event to be monitored; according to the basic event data and a historical event database, obtaining predicted event popularity data of the to-be-monitored event; according to the predicted event popularity data, obtaining an initial popularity map of the to-be-monitored event; obtaining an initial video data set of the target low-altitude aircraft; according to the initial video data set and the initial popularity map, obtaining an intermediate popularity map set of the to-be-monitored event; according to the intermediate popularity atlas, obtaining a target endurance duration of the target air aircraft; it can be known that the endurance prediction can be continuously corrected along with the progress of the event, even if the evolution of the event deviates from the initial expectation, the system can also rapidly adjust, the prediction result is always kept to be highly matched with the actual situation, and the robustness and adaptability of the method in a complex and uncertain scene are remarkably improved.

Description

Technical Field

[0001] This disclosure relates to the field of low-altitude aircraft technology, specifically to a method, device, and medium for calculating the endurance of a low-altitude aircraft. Background Technology

[0002] With the rapid development of the low-altitude economy, low-altitude aircraft such as drones are increasingly being used in public safety monitoring, large-scale event support, and traffic flow monitoring. When performing these area monitoring tasks, the endurance of the aircraft is a key bottleneck restricting their mission effectiveness. Especially when dealing with dynamically changing mass events such as concerts, sporting events, and emergency evacuations, monitoring needs exhibit high uncertainty in time and space. Traditional flight plans based on fixed routes or simple area patrols often fail to accurately match the energy consumption demands of the evolving event, leading to premature aircraft return to base, gaps in monitoring coverage, or, for conservative reasons, over-deployment of aircraft, resulting in resource waste.

[0003] Existing technologies have yielded some research on optimizing the endurance of low-altitude aircraft. For example, some solutions reduce ineffective flight distance by optimizing flight paths or allocate power based on the fixed area of ​​the mission zone. Other solutions focus on the aircraft's own energy management, such as reducing power consumption by adjusting flight speed and altitude. However, most of these methods are based on static or predefined mission models and fail to fully consider the dynamic evolution of the monitored events themselves. The temporal and spatial changes in the "heat" of an event (such as crowd density and movement trends) directly determine the monitoring focus and the aircraft's workload. If the future trend of event heat cannot be predicted and the monitoring strategy cannot be dynamically adjusted accordingly, endurance optimization will lack a fundamental basis. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a method, device and medium for calculating the endurance of a low-altitude aircraft.

[0005] The first aspect provides a method for calculating the endurance of a low-altitude aircraft, the method comprising: S100 receives the basic event data corresponding to the event to be monitored; S200, Based on the basic event data and historical event database, obtain the predicted event popularity data of the event to be monitored; S300, Based on the predicted event popularity data, obtain the initial popularity map of the event to be monitored; S400, acquire the initial video dataset of the target low-altitude aircraft; S500, based on the initial video dataset and the initial heatmap, obtain the intermediate heatmap set of the event to be monitored; S600: Based on the intermediate heat map, obtain the target endurance of the target airborne vehicle.

[0006] This application provides a method for calculating the endurance of a low-altitude aircraft. The method involves receiving basic event data corresponding to a monitored event; obtaining predicted event heat data for the monitored event based on the basic event data and a historical event database; obtaining an initial heatmap of the monitored event based on the predicted event heat data; obtaining an initial video dataset of the target low-altitude aircraft; obtaining an intermediate heatmap set of the monitored event based on the initial video dataset and the initial heatmap; and obtaining the target endurance of the target low-altitude aircraft based on the intermediate heatmap set. This method provides an accurate estimate of the energy required to complete a specific monitoring task, rather than a simple calculation of battery physical capacity, fundamentally solving the problem of blind and inaccurate endurance planning in dynamic scenarios. Furthermore, it allows the endurance prediction to be continuously corrected as the event progresses. Even if the event deviates from the initial expectation, the system can quickly adjust, always maintaining a high degree of consistency between the prediction results and the actual situation, significantly improving the robustness and adaptability of the method in complex and uncertain scenarios.

[0007] A second aspect provides a computer device including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method of the first aspect.

[0008] A third aspect provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method of the first aspect. Attached Figure Description

[0009] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 A flowchart illustrating the steps of a method for calculating the endurance of a low-altitude aircraft provided in this application; Figure 2 A flowchart illustrating the steps of another method for calculating the endurance of a low-altitude aircraft provided in this application; Figure 3 A flowchart illustrating the steps of another method for calculating the endurance of a low-altitude aircraft provided in this application; Figure 4 A flowchart illustrating the steps of another method for calculating the endurance of a low-altitude aircraft provided in this application; Figure 5 A flowchart illustrating the steps of a method for calculating the endurance of a low-altitude aircraft provided in this application. Detailed Implementation

[0010] It should be noted that all user data (including but not limited to user device data, user personal data, object data corresponding to device usage data, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, device usage data, etc.) involved in all embodiments of this disclosure are data and data authorized by the user or fully authorized by all parties.

[0011] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0012] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0013] Example 1 like Figure 1 As shown in the figure, this embodiment provides a method for calculating the endurance of a low-altitude aircraft, the method including: S100 receives the basic event data corresponding to the event to be monitored.

[0014] Specifically, the event to be monitored refers to an event provided by the target server that needs to be monitored by a low-altitude aircraft; further understood: the target server is the user's server.

[0015] Preferably, the event type of the event to be monitored is a clustered event, such as a concert or outdoor performance.

[0016] Specifically, the basic event data includes: the initial geographical area of ​​the event to be monitored, the initial number of roads to be monitored, the initial pedestrian flow to be monitored, and the initial vehicle flow to be monitored.

[0017] S200: Based on the basic event data and historical event database, obtain the predicted event popularity data of the event to be monitored.

[0018] Specifically, the historical event database includes several historical event data and historical popularity correlation data corresponding to each historical event; wherein, the historical popularity correlation data includes: historical heat map, historical monitoring area location, and historical pedestrian flow distribution.

[0019] like Figure 2 As shown, step S200 also includes the following steps: S201, The basic event data is vectorized to generate an initial event feature vector for the event to be monitored; S202, vectorize each historical event data to generate a historical event feature vector; S203, based on the initial event feature vector and all historical event feature vectors, obtain a first similarity set corresponding to the monitored event, wherein the first similarity set includes: several first similarities corresponding to the monitored event, and the first similarity is the similarity between the initial event feature vector and any historical event feature vector; those skilled in the art know any method of obtaining the similarity between vectors in the prior art, and will not be described in detail here; for example, the first similarity is obtained by using cosine similarity.

[0020] Iterate through the first similarity set and use the historical popularity association data corresponding to the largest first similarity as the predicted event popularity data.

[0021] S300, Based on the predicted event heat data, obtain the initial heat map of the event to be monitored.

[0022] like Figure 3 As shown, step S300 also includes the following steps: S301, the historical heat map in the predicted event heat data is used as the first heat map; S302, process the first heatmap to obtain the second heatmap; S303, Based on the location of historical monitoring areas and the distribution of historical pedestrian flow in the predicted event heat map, generate heat correction parameters for each geographic grid in the second heat map; S304, Generate the initial heat map based on the heat correction parameters and the second heat map.

[0023] Preferred, step S302 also includes the following steps: S3021, Obtain the geographical area of ​​the historical event from the historical event data corresponding to the largest first similarity; S3022, Based on the initial geographic area and the geographic area of ​​the historical event, obtain the geographic area scaling ratio, wherein the geographic area scaling ratio is the ratio between the initial geographic area and the geographic area of ​​the historical event. S3023, adjust the first heat map according to the geographic region scaling ratio to generate the second heat map.

[0024] Preferred, step S303 also includes the following steps: S3031, Based on the historical monitoring area location set, obtain the first heat index influence factor corresponding to each historical monitoring area; further understood as: historical monitoring area location set L = {L1, ..., L...}r , ..., L s}, L r This is the location of the r-th historical monitoring area, where r ranges from 1 to s, and s is the number of historical monitoring areas, with s≥2; where the historical monitoring area is a geographic grid within the geographic region of a historical event; according to L r , obtain L r The corresponding first popularity influence factor U r , among which, U r The following conditions must be met: d() is the Euclidean distance function, K() is the Gaussian kernel function, and L0 It is the location of the central historical monitoring area within L; h is the bandwidth parameter and h meets the following conditions: S 0 η is the geographical area of ​​the historical event, and η is an adjustment coefficient and η∈[0,1].

[0025] Preferably, η=0.9.

[0026] S3032, based on historical pedestrian flow distribution, obtain the second heat index influencing factor corresponding to each historical monitoring area; further understood as: historical pedestrian flow distribution set P = {P1, ..., P...} r ..., P s}, P r It is the number of people in the r-th historical monitoring area; according to P r , obtain P r The corresponding first popularity influence factor Q r , where Q r The following conditions must be met: P max It is the maximum value in P, P min It is the minimum value in P.

[0027] S3033, based on the first heat influence factor and the second heat influence factor, obtain the heat correction parameters for the geographic grids in the second heat map; further understood as: the heat correction parameter W for the r-th geographic grid in the initial heat map. r Among them, W r The following conditions must be met: Norm is the normalization function.

[0028] Specifically, in step S304, the initial heat value of the geographic grid in the initial geographic area is obtained based on the heat correction parameter of the geographic grid in the second heat map and the heat value corresponding to the historical monitoring area; further understood as: the initial heat value of the geographic grid in the initial geographic area is obtained by multiplying the heat correction parameter of the geographic grid in the initial heat map and the heat value corresponding to the historical monitoring area.

[0029] Furthermore, the geographic grids in the initial geographic region correspond one-to-one with the historical monitoring areas.

[0030] As described above, by utilizing a historical event database, similar historical cases are intelligently matched based on the initial attributes of the current event, and their "heat" (such as pedestrian flow distribution and areas of interest) evolution data is extracted as a basis for prediction, thereby generating an initial heat map. This method elevates the planning of battery life from a consideration of static geographical areas to a prediction of the dynamic life cycle of events. This ensures that the final calculated "target battery life" truly reflects the theoretical time required to complete this specific monitoring task, rather than simply the physical battery life, greatly improving the accuracy and reliability of the planning.

[0031] S400: Obtain the initial video dataset of the target low-altitude aircraft.

[0032] Specifically, the initial video dataset includes initial video data collected by the target low-altitude aircraft within several preset time slots, and the initial video data is video data within the geographical area corresponding to the event to be monitored.

[0033] S500: Based on the initial video dataset and the initial heatmap, obtain the intermediate heatmap set of the event to be monitored.

[0034] like Figure 4 As shown, step S500 also includes the following steps: S501, perform image analysis on the initial video data of each preset time slice to obtain the distribution of people within the preset time slice; S502, the heat map of the current time slice is obtained by fusing the pedestrian flow distribution within the preset time slice with the heat map corresponding to the previous preset time slice. S503, the updated heatmaps of the preset time slices are arranged in chronological order to form the intermediate heatmap set.

[0035] Specifically, step S501 includes: S5011, randomly extract images from the initial video data within each preset time slice to construct an initial event image set A={A1, ..., A...} i , ..., A m}, A i ={Ai1 , ..., A ij , ..., A in}, A ij It is the j-th initial event image within the i-th preset time slice, where i ranges from 1 to m, m is the number of preset time slices and m≥2, j ranges from 1 to n, and n is the number of images extracted per second within each preset time slice and n≥2; S5012, for A ij Perform image analysis to obtain A ij The corresponding set of identified people B ij ={B 1 ij , ..., B r ij , ..., B s ij}, B r ij A is the actual geographic area of ​​the event to be monitored. ij The number of people in the corresponding r-th geographic grid; S5013, Based on A, obtain the pedestrian flow distribution D within the preset time slice. i ={D i1 , ..., D ir , ..., D is}, where D ir It represents the number of the r-th character within the i-th preset time slice.

[0036] Preferably, when hour, ; hour, Where △K is a preset threshold for the uniformity of pedestrian flow distribution.

[0037] Specifically, step S502 includes: S5021, when i=1, obtain the initial heat value G={G1, ..., G...} within the geographic grid in the initial heat map. r , ..., G s}, G r It is the initial heat value within the r-th geographic grid; S5022, according to G r and D 1r , obtain G r The corresponding updated heatmap shows the median heat value G within the r-th geographic grid. 0 1r Among them, G 0 r The following conditions must be met: , where D 01r It is the number of people in the r-th geographic grid in the initial heatmap; based on each G 0 1r Construct the updated heatmap within the first preset time slice; S5023, Repeat steps S5021 and S5022 to obtain the updated heatmap for each preset time slice.

[0038] As described above, this application not only performs prior historical data prediction (generating an initial heatmap), but also incorporates real-time video data transmitted back by the aircraft for observation. Furthermore, it uses an algorithm to fuse the observed real-time pedestrian flow distribution with the predicted heatmap, dynamically updating and generating an intermediate heatmap set. This closed-loop mechanism enables the system to continuously correct prediction biases, ensuring that the heatmap and its-based endurance predictions always closely reflect the actual evolution of the event, thus enhancing the system's adaptability and robustness in complex dynamic scenarios.

[0039] S600: Based on the intermediate heat map, obtain the target endurance of the target airborne vehicle.

[0040] like Figure 5 As shown, step S600 also includes the following steps: S601, feature extraction is performed on each intermediate heat map in the intermediate heat map set to obtain the heat feature vector of the event to be monitored. The heat feature vector includes: the rate of change of the total heat value, the rate of change of the heat of the geographic grid, and the maximum value of the heat change rate. S602 calculates the target's endurance based on the heat feature vector of the event to be monitored and the current battery level of the target low-altitude aircraft.

[0041] Preferably, the rate of change of the total heat value is F1, and F1 meets the following conditions: .

[0042] Preferably, the heat change rate of the geographic grid is F2={F 21 , ..., F 2r , ..., F 2s}, F 2r F is the rate of change of heat within the r-th geographic grid. 2r The following conditions must be met: .

[0043] Preferably, the maximum value of the rate of change of heat is F3, where F3 = Max(F2).

[0044] Specifically, step S602 includes: S6021, Obtain the current battery level C of the target low-altitude aircraft; S6022, Based on C, obtain the hovering time T of the target low-altitude aircraft; S6023, obtain the target battery life T based on T and the heat feature vector of the event to be monitored. 0 T 0 The following conditions must be met: Where α is the first parameter, β is the second parameter, and δ is the third parameter; those skilled in the art can set the parameters according to actual needs.

[0045] Preferably, α=0.6, β=0.3, δ=0.2.

[0046] F 0 2. Meets the following conditions: .

[0047] As described above, by predicting the hotspots of events and their changing trends, more efficient monitoring paths and focus-station strategies can be planned for aircraft, concentrating their power consumption on truly high-value monitoring tasks. This avoids ineffective patrols and wasted power due to unclear tasks, effectively extending the effective mission time of a single aircraft while ensuring monitoring coverage of key areas. It also reduces the need for excessive deployment of backup aircraft to cover the entire event cycle, thereby lowering overall operating costs.

[0048] This application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method of Embodiment 1.

[0049] This application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method of Embodiment 1.

[0050] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for calculating the endurance of a low-altitude aircraft, characterized in that, The method includes: S100 receives the basic event data corresponding to the event to be monitored; S200, Based on the basic event data and historical event database, obtain the predicted event popularity data of the event to be monitored; S300, Based on the predicted event popularity data, obtain the initial popularity map of the event to be monitored; S400, acquire the initial video dataset of the target low-altitude aircraft; S500, based on the initial video dataset and the initial heatmap, obtain the intermediate heatmap set of the event to be monitored; S600: Based on the intermediate heat map, obtain the target endurance of the target low-altitude aircraft.

2. The method for calculating the endurance of a low-altitude aircraft according to claim 1, characterized in that, The events to be monitored refer to events provided by the target server that require monitoring by low-altitude aircraft.

3. The method for calculating the endurance of a low-altitude aircraft according to claim 2, characterized in that, The event type of the event to be monitored is a clustered event.

4. The method for calculating the endurance of a low-altitude aircraft according to claim 1, characterized in that, The historical event database includes several historical event data and historical popularity correlation data corresponding to each historical event; wherein, the historical popularity correlation data includes: historical heat map, historical monitoring area location and historical pedestrian flow distribution.

5. The method for calculating the endurance of a low-altitude aircraft according to claim 4, characterized in that, The S200 procedure also includes the following steps: S201, The basic event data is vectorized to generate an initial event feature vector for the event to be monitored; S202, vectorize each historical event data to generate a historical event feature vector; S203, based on the initial event feature vector and all historical event feature vectors, obtain the first similarity set corresponding to the monitored event, wherein the first similarity set includes: several first similarities corresponding to the monitored event, and the first similarity is the similarity between the initial event feature vector and any historical event feature vector; S204, traverse the first similarity set and use the historical popularity association data corresponding to the largest first similarity as the predicted event popularity data.

6. The method for calculating the endurance of a low-altitude aircraft according to claim 4, characterized in that, The S300 procedure also includes the following steps: S301, the historical heat map in the predicted event heat data is used as the first heat map; S302, process the first heatmap to obtain the second heatmap; S303, Based on the location of historical monitoring areas and the distribution of historical pedestrian flow in the predicted event heat map, generate heat correction parameters for each geographic grid in the second heat map; S304, Generate the initial heat map based on the heat correction parameters and the second heat map.

7. The method for calculating the endurance of a low-altitude aircraft according to claim 6, characterized in that, Step S302 also includes the following steps: S3021, Obtain the geographical area of ​​the historical event from the historical event data corresponding to the largest first similarity; S3022, Based on the initial geographic area and the geographic area of ​​the historical event, obtain the geographic area scaling ratio, wherein the geographic area scaling ratio is the ratio between the initial geographic area and the geographic area of ​​the historical event. S3023, adjust the first heat map according to the geographic region scaling ratio to generate the second heat map.

8. The method for calculating the endurance of a low-altitude aircraft according to claim 6, characterized in that, Step S303 also includes the following steps: S3031, Based on the historical monitoring area location set, obtain the first heat influence factor corresponding to each historical monitoring area; S3032, based on historical pedestrian flow distribution, obtain the second heat index influencing factor corresponding to each historical monitoring area; S3033, Based on the first heat influence factor and the second heat influence factor, obtain the heat correction parameters for each geographic grid in the second heat map.

9. The method for calculating the endurance of a low-altitude aircraft according to claim 1, characterized in that, The initial video dataset includes initial video data collected by the target low-altitude aircraft within several preset time slots. The initial video data is video data within the geographical area corresponding to the event to be monitored.

10. The method for calculating the endurance of a low-altitude aircraft according to claim 5, characterized in that, The S500 procedure also includes the following steps: S501, perform image analysis on the initial video data of each preset time slice to obtain the distribution of people within the preset time slice; S502, the heat map of the current time slice is obtained by fusing the pedestrian flow distribution within the preset time slice with the heat map corresponding to the previous preset time slice. S503, the updated heatmaps of the preset time slices are arranged in chronological order to form the intermediate heatmap set.

11. The method for calculating the endurance of a low-altitude aircraft according to claim 1, characterized in that, The S600 procedure also includes the following steps: S601, feature extraction is performed on each intermediate heat map in the intermediate heat map set to obtain the heat feature vector of the event to be monitored. The heat feature vector includes: the rate of change of the total heat value, the rate of change of the heat of the geographic grid, and the maximum value of the heat change rate. S602 calculates the target's endurance based on the heat feature vector of the event to be monitored and the current battery level of the target low-altitude aircraft.

12. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 11.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 11.

Images