Unmanned aerial vehicle multi-source heterogeneous data fusion method and system based on three-dimensional scene

Abstract

The invention discloses an unmanned aerial vehicle multi-source heterogeneous data fusion method and system based on a three-dimensional scene. Relates to the technical field of multi-source heterogeneous data fusion. The method comprises the following steps: step 1, acquiring flight data of an unmanned aerial vehicle and three-dimensional scene data; 2, the flight data of the unmanned aerial vehicle and the three-dimensional scene data are preprocessed; 3, calculating a topological matching degree according to the preprocessed flight data of the unmanned aerial vehicle and the three-dimensional scene data; step 4, calculating a fusion weight of the flight data of the unmanned aerial vehicle and the three-dimensional scene data according to the topological matching degree in combination with a joint probability density correlation model; and 5, fusing the flight data of the unmanned aerial vehicle and the three-dimensional scene data according to the fusion weight, and visualizing a fusion result. According to the method, the data credibility can be effectively improved, spatial consistent data is screened through the topological matching degree, the credibility is quantified in combination with the joint probability density model, and the problem of unmanned aerial vehicle sensor errors and modeling deviation of a three-dimensional scene is avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of multi-source heterogeneous data fusion, and more particularly to a UAV multi-source heterogeneous data fusion method and system based on a three-dimensional scene. BACKGROUND

[0002] At present, existing patents only process two-dimensional monitoring data of UAVs (such as two-dimensional flight path, device state, and planar coordinate data), and cannot be compatible with three-dimensional scene data in the UAV operation scene (such as three-dimensional laser radar point cloud, oblique photography three-dimensional image, and digital elevation model (DEM) terrain data), resulting in a lack of stereoscopic dimension of two-dimensional monitoring + three-dimensional space in the fusion result, and the fusion result cannot support precise operation and monitoring of UAVs in complex three-dimensional scenes (such as between city high-rise buildings and mountainous areas).

[0003] Although the joint probability density correlation model can realize correlation at the two-dimensional data level (such as probability matching of flight path and planar position data), it does not combine the spatial topological relationship of the three-dimensional scene (such as the height difference between the UAV flight path and the three-dimensional terrain, and the spatial overlap between the three-dimensional point cloud and the UAV monitoring target), resulting in insufficient fusion accuracy in the three-dimensional scene, for example, it is unable to accurately determine whether the UAV flight path is below the mountain elevation and has a collision risk.

[0004] Therefore, it is an urgent problem for those skilled in the art to design a UAV multi-source heterogeneous data fusion method and system based on a three-dimensional scene, and to realize multi-element heterogeneous fusion of two-dimensional monitoring data and three-dimensional scene data of UAVs. SUMMARY

[0005] Therefore, the present application provides a UAV multi-source heterogeneous data fusion method and system based on a three-dimensional scene, which can effectively improve data reliability, filter spatial consistent data through topological matching degree, and combine a joint probability density model to quantify reliability, thereby avoiding problems of UAV sensor errors and modeling deviations of the three-dimensional scene.

[0006] To achieve the above purpose, the present application adopts the following technical solution: a UAV multi-source heterogeneous data fusion method based on a three-dimensional scene, comprising: Step 1: obtaining UAV flight data and three-dimensional scene data; Step 2: respectively pre-processing the UAV flight data and the three-dimensional scene data; Step 3: calculating a topological matching degree according to the pre-processed UAV flight data and the three-dimensional scene data; Step 4: calculating a fusion weight of the UAV flight data and the three-dimensional scene data according to the topological matching degree and a joint probability density correlation model; Step 5: Fuse the UAV flight data and the three-dimensional scene data according to the fusion weight, and visualize the fusion result.

[0007] Preferably, the UAV flight data includes GPS longitude and latitude, altitude, flight speed, and sampling timestamp. The process of pre-processing the UAV flight data includes data format standardization, missing value and abnormal value processing, coordinate system unification, data resampling, and noise filtering.

[0008] Preferably, the three-dimensional scene data includes a terrain model, a scene grid, and a texture map. The process of pre-processing the three-dimensional scene data includes data lightweight and redundancy elimination, geometric error correction, coordinate and resolution unification, and invalid area mask processing. The pre-processed UAV flight data and the pre-processed three-dimensional scene data are subjected to consistency checking.

[0009] Preferably, the process of calculating the topological matching degree in step 3 includes calculating the elevation difference and the spatial overlap degree according to the pre-processed UAV flight data and the three-dimensional scene data, and integrating the elevation difference and the spatial overlap degree by weight to obtain the final topological matching degree.

[0010] Preferably, the process of calculating the elevation difference includes: Spatial position alignment: taking the coordinate system of the three-dimensional scene data as the reference, mapping the UAV flight data to the same coordinate system through coordinate conversion to ensure the spatial position correspondence of the two; Selecting sampling points: selecting N sampling points at fixed intervals in the overlapping area of the UAV flight data and the three-dimensional scene data fusion scene, covering the entire data area; Calculating the elevation difference: calculating the elevation difference of each point, and using the average elevation difference or the maximum elevation difference to represent the overall vertical matching degree.

[0011] Preferably, the process of calculating the spatial overlap degree includes: Extracting the region boundary: extracting the minimum circumscribed rectangle S 无人机 from the UAV flight data to extract the corresponding effective scene boundary S 场景 from the three-dimensional scene data. Calculating the overlapping area and the total area: using spatial geometric algorithm to calculate the intersection area S 重叠 of the UAV region and the three-dimensional scene region, and calculating the union area S 并集 =S 无人机 +S 场景 -S 重叠 . Calculating the spatial overlap degree: S 空间重叠度 =S重叠 / S 并集 ; The topological matching degree is calculated by weighting the height difference and the spatial overlap.

[0012] Preferably, the calculation process of the fusion weight comprises: extracting the height difference and the spatial overlap in the topological matching degree, and inputting the same as constraint conditions into the joint probability density correlation model; constructing a joint probability density function of a two-dimensional normal distribution based on the mean, variance and joint covariance of the observation errors of the preprocessed UAV flight data and the three-dimensional scene data respectively, and calculating the initial probability density value of each spatial sampling point; weighting and correcting the initial probability density value by using the topological matching degree, and strengthening the probability contribution of the high matching degree data; normalizing the corrected probability density value to obtain the fusion weight corresponding to each sampling point, and the fusion weight has a value range of [0, 1].

[0013] Preferably, the expression of the joint probability density correlation model is: ; wherein x is the observation value of the preprocessed UAV flight data at a target sampling point, y is the observation value of the preprocessed three-dimensional scene data at the same target sampling point, f(x, y) is the joint probability density value of the two types of data at the sampling point; μ1 is the mean of the height error of the UAV flight data; σ1 2 is the height error variance of the UAV flight data; μ2 is the mean of the height error of the three-dimensional scene data; σ2 2 is the height error variance of the three-dimensional scene data; ρ is the joint error covariance, which is determined by analyzing the error correlation of the two types of data in historical matching samples.

[0014] Preferably, the formula for weighting and correcting the initial probability density value by using the topological matching degree is as follows: F’(x, y) = f(x, y) × [0.5 + 0.5 × M]; wherein 0.5 is a basic weight coefficient, and 0.5 × M is a topological matching degree contribution weight; M is the topological matching degree.

[0015] Preferably, a UAV multi-source heterogeneous data fusion system based on a three-dimensional scene comprises: a data acquisition module for acquiring UAV flight data and three-dimensional scene data; a preprocessing module for preprocessing the UAV flight data and the three-dimensional scene data respectively; a topological matching degree calculation module for calculating a topological matching degree according to the preprocessed UAV flight data and the three-dimensional scene data. a model calculation module, configured to calculate a fusion weight of the UAV flight data and the three-dimensional scene data according to the topological matching degree in combination with a joint probability density correlation model; a visualization module, configured to fuse the UAV flight data and the three-dimensional scene data according to the fusion weight, and visualize the fusion result.

[0016] According to the technical solution, compared with the prior art, the application provides a UAV multi-source heterogeneous data fusion method and system based on a three-dimensional scene, and has the following specific beneficial effects: 1. Improving data reliability and reducing single data source error risk: through topological matching degree calculation, the basic data with high spatial consistency is first screened, and then the joint probability density correlation model is combined to quantify the data reliability, so as to avoid the influence of UAV sensor errors (such as height fluctuation caused by air flow interference) or three-dimensional scene modeling deviation (such as splicing joint error) on the fusion result, and the data reliability is significantly improved compared with the single use of UAV or three-dimensional scene data.

[0017] 2. Improving fusion accuracy and realizing accurate matching of spatial information: through the progressive design of coordinate unification-topological matching-probability weighting, it is ensured that the UAV data and the three-dimensional scene data are highly matched in spatial position (horizontal overlap), height information (vertical deviation), and the fusion weight is strongly associated with the data quality (high matching degree data weight is higher), which meets the high-precision scene requirements of surveying and mapping, inspection and other scenes, and is superior to the accuracy performance of the traditional simple average fusion method.

[0018] 3. Enhancing data adaptability and adapting to the needs of multiple scene applications: the method of the application supports processing different types of UAV data (such as GPS trajectory, height sampling value) and three-dimensional scene data (such as DEM terrain model, oblique photography three-dimensional grid), and the fusion strictness can be flexibly adjusted through the weight threshold value - for example, in the emergency rescue scene, the threshold value can be relaxed to quickly obtain the fusion result; in the precise surveying and mapping scene, the threshold value can be increased to ensure data accuracy, and adapt to the differentiated needs of different industries (such as geographic surveying and mapping, power inspection, digital twin). BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0020] Figure 1 The method flowchart provided by the application. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0022] As shown in the figure, the embodiment of the present application discloses a multi-source heterogeneous data fusion method of unmanned aerial vehicle based on three-dimensional scene, comprising: Figure 1 Step 1: obtaining unmanned aerial vehicle flight data and three-dimensional scene data; Step 2: respectively pre-processing the unmanned aerial vehicle flight data and three-dimensional scene data; Step 3: calculating the topological matching degree according to the pre-processed unmanned aerial vehicle flight data and three-dimensional scene data; Step 4: the fusion weight of unmanned aerial vehicle flight data and three-dimensional scene data; Step 5: fusing the unmanned aerial vehicle flight data and three-dimensional scene data according to the fusion weight, and visualizing the fusion result.

[0023] Specifically, the unmanned aerial vehicle flight data includes GPS longitude and latitude, altitude, flight speed and sampling timestamp. The process of pre-processing the unmanned aerial vehicle flight data includes data format standardization, missing value and abnormal value processing, coordinate system unification, data resampling and noise filtering.

[0024] In a specific embodiment of the present application, the missing value and abnormal value processing includes: The missing value is caused by the loss of GPS signal (such as shielding, high-rise building), resulting in the field of part of data points being empty (such as missing altitude).

[0025] Small amount of missing values (<5%): linear interpolation method is used to complete (such as filling the missing value with the average of the altitudes of the two normal points before and after). Large amount of missing values (>10%): directly deleting the data in this section (avoiding the accumulation of interpolation error).

[0026] The abnormal value is caused by sensor error and sudden interference, resulting in data jump (such as the altitude suddenly changing from 100m to 500m, or the longitude and latitude exceeding the actual flight area).

[0027] Using 3σ principle to identify: calculating the mean (μ) and standard deviation (σ) of a field (such as altitude), and removing the abnormal points with "value>μ+3σ" or "value<μ-3σ"; ​Spatial rationality verification: combined with the flight area boundary (such as the pre-set north latitude 30~30.5°, east longitude 120°~120.5°), delete the abnormal data points beyond the boundary.

[0028] Coordinate system unification takes the coordinate system of the three-dimensional scene data as the reference, and the unmanned aerial vehicle data is converted through professional tools (such as ArcGIS, QGIS): WGS84 longitude and latitude→UTM plane coordinate (such as UTM Zone 50N); Geodetic height→normal height (if the three-dimensional scene uses the altitude height, the "geoid difference" of the region needs to be subtracted to ensure the uniformity of the height reference).

[0029] Further, the data resampling includes spatial resampling and time resampling; Among them, the spatial resampling takes the pixel grid of the three-dimensional scene as the unit, and calculates the average height / position of all unmanned aerial vehicle data points in the grid by using the mean method or the median method, so that one scene grid corresponds to one unmanned aerial vehicle data point; Time resampling (if time sequence matching is needed): if the three-dimensional scene is time sequence data (such as terrain change at different times), the average value of the data in the corresponding time period of the unmanned aerial vehicle is extracted according to the time interval of the scene (such as 1 hour / frame), and the time-space double alignment is realized.

[0030] Specifically, the three-dimensional scene data includes: a terrain model, a scene grid and a texture map; The process of pre-processing the three-dimensional scene data includes: data lightweight and redundancy elimination, geometric error correction, coordinate and resolution unification, and invalid area mask mask processing; The pre-processed unmanned aerial vehicle flight data and the pre-processed three-dimensional scene data are subjected to consistency verification.

[0031] Specifically, the process of calculating the topological matching degree in step 3 includes: calculating the height difference and spatial overlap degree according to the pre-processed unmanned aerial vehicle flight data and three-dimensional scene data, integrating the height difference and spatial overlap degree according to the weight, and obtaining the final topological matching degree.

[0032] In a specific embodiment of the present application, after the pre-processing of the two types of data is completed, consistency verification is performed to ensure that the subsequent calculation requirements are met, which specifically includes: Spatial range verification: check whether the coverage range of the unmanned aerial vehicle data is completely within the coverage range of the three-dimensional scene data (allowing ±5% of the edge to exceed, and the exceeding part needs to be cut); Accuracy verification: randomly select 100 sampling points to check the "coordinate deviation" (such as UTM coordinate X / Y deviation <0.5 meters) and "height reference deviation" (such as root mean square error RMSE <0.3 meters) of the two types of data. Format validation: Confirm that both types of data are in a "readable, universal format" (e.g., GeoJSON for drones and LAS / OBJ for 3D scenes), and that field / attribute information is complete and without missing information.

[0033] Once the verification is successful, the data can be used to calculate the topology matching degree.

[0034] Specifically, the process of calculating the elevation difference includes: Spatial alignment: Using the coordinate system of the 3D scene data as a reference, the UAV flight data is mapped to the same coordinate system through coordinate transformation to ensure that the spatial positions of the two correspond. Sampling point selection: Select N sampling points at fixed intervals within the overlapping area of ​​the fused scene of UAV flight data and 3D scene data to cover the entire data area; Calculate elevation difference: Calculate the elevation difference of each point, and use the average elevation difference or the maximum elevation difference to characterize the overall vertical matching degree.

[0035] Specifically, the process of calculating spatial overlap includes: Extracting the region boundary: Extracting the minimum bounding rectangle S of the flight trajectory from the UAV flight data. 无人机 Extract the corresponding effective scene boundary S from the 3D scene data 场景 ; Calculate the overlapping area and the total area: Use spatial geometry algorithms to calculate the intersection area S between the drone region and the 3D scene region. 重叠 Calculate the area S of the union of the two sets. 并集 =S 无人机 +S 场景 -S 重叠 ; Calculate spatial overlap: S 空间重叠度 =S 重叠 / S 并集 ; The topology matching degree is obtained by weighting the elevation difference and spatial overlap.

[0036] Specifically, the calculation process for the fusion weights includes: The elevation difference and spatial overlap in the topological matching degree are extracted and used as constraints input into the joint probability density association model. Based on the mean, variance, and joint covariance of the observation errors of the preprocessed UAV flight data and 3D scene data, a joint probability density function of a two-dimensional normal distribution is constructed, and the initial probability density value of each spatial sampling point is calculated. The initial probability density value is weighted and corrected using the topological matching degree to enhance the probability contribution of high-matching data. The corrected probability density values ​​are normalized to obtain the fusion weights corresponding to each sampling point. The fusion weights range from [0, 1].

[0037] Specifically, the expression for the joint probability density association model is: ; Where x represents the preprocessed UAV flight data observation at the target sampling point, y represents the preprocessed 3D scene data observation at the same target sampling point, f(x,y) is the joint probability density value of the two types of data at that sampling point; μ1 is the mean elevation error of the UAV flight data; σ1 2 σ² represents the elevation error variance of the UAV flight data; μ² represents the mean elevation error of the 3D scene data; σ² represents the mean elevation error of the UAV flight data. 2 ρ represents the elevation error variance of the 3D scene data; ρ represents the joint error covariance, which is determined by analyzing the error correlation between the two types of data in historical matching samples.

[0038] Specifically, the formula for weighting and correcting the initial probability density value using the topological matching degree is as follows: F'(x,y)=f(x,y)×[0.5+0.5×M]; Where 0.5 is the basic weight coefficient, and 0.5×M is the contribution weight of topology matching degree; M is the topology matching degree.

[0039] In a specific embodiment of the present invention, this embodiment takes the preliminary surveying and mapping scenario of the renovation of an old residential area in a certain city as the background. It is necessary to integrate the on-site surveying and mapping data of UAVs with the existing three-dimensional planning model data of the residential area to provide accurate spatial reference for the renovation plan design. The specific implementation process is as follows: Sampling point selection: In the overlapping areas of the community, 1,000 sampling points were evenly selected in a 2m x 2m grid to cover key areas such as building tops, road surfaces, and green areas to ensure that the sampling points are representative.

[0040] Elevation difference calculation: For each sampling point, extract the elevation value (H1) of the UAV DSM and the elevation value (H2) of the 3D scene elevation raster map, and calculate the elevation difference ΔH=|H1-H2|.

[0041] Spatial overlap calculation: Using ArcGIS software, extract the minimum bounding rectangle of the UAV-mapped area (area S1 = 82,000 square meters) and the minimum bounding rectangle of the area covered by the 3D scene model (area S2 = 85,000 square meters), and calculate the intersection area S. 重叠 =79,000 square meters, spatial overlap = S 重叠 / (S1+S2-S 重叠 =7.9 / (8.2+8.5-7.9)≈0.89.

[0042] The comprehensive topological matching degree calculation: set the elevation difference weight 0.5, the spatial overlap weight 0.5, substitute into the formula: topological matching degree M=(1- average elevation difference) x 0.5+ spatial overlap x 0.5=(1-0.23) x 0.5+0.96 x 0.5≈0.865. 0.865>0.6, therefore, it can be proved that the elevation difference and the spatial overlap are effective fusion. Further, based on the preprocessed data, it is obtained that: the elevation error mean of the unmanned aerial vehicle DSM data μ1=0.15 meters, the error variance σ1 2 =0.03; the elevation error mean of the three-dimensional scene data μ2=0.10 meters, the error variance σ2 2 =0.02; through the historical data statistics of the same type of project, the joint error covariance of the two types of data ρ=0.25.

[0043] With the topological matching degree M=0.865 as the constraint, for each sampling point, substitute into the two-dimensional normal distribution joint probability density formula:

[0044] When x=0.2, y=0.15, the final f(x,y)≈6.21, which indicates that the probability of the sampling point belonging to the same associated target of the two types of data is extremely high at the statistical level, and the final fusion weight will also reach 0.865 due to the high probability density 0.5+0.95 0.5=0.9075; (assuming that the probability density is normalized to 0.95), far exceeding the effective fusion threshold (such as the 0.6 set in the foregoing), directly supporting the decision that the sampling point can participate in effective fusion.

[0045] Finally, QGIS software is used for visualization.

[0046] Specifically, an unmanned aerial vehicle multi-source heterogeneous data fusion system based on a three-dimensional scene comprises: A data acquisition module: acquiring unmanned aerial vehicle flight data and three-dimensional scene data; A preprocessing module: preprocessing the unmanned aerial vehicle flight data and the three-dimensional scene data respectively; A topological matching degree calculation module: calculating a topological matching degree according to the preprocessed unmanned aerial vehicle flight data and the three-dimensional scene data; A model calculation module: used for calculating a fusion weight of the unmanned aerial vehicle flight data and the three-dimensional scene data according to the topological matching degree and a joint probability density association model; A visualization module: used for fusing the unmanned aerial vehicle flight data and the three-dimensional scene data according to the fusion weight, and visualizing the fusion result.

[0047] The various embodiments described in this specification are implemented in a progressive manner, each embodiment focusing on the differences from other embodiments, and the same or similar parts between embodiments can be mutually referred to. For the apparatus disclosed by the embodiments, since it corresponds to the method disclosed by the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0048] The above description of disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for fusing multi-source heterogeneous data from UAVs based on 3D scenes, characterized in that, include: Step 1: Acquire drone flight data and 3D scene data; Step 2: Preprocess the UAV flight data and 3D scene data respectively; Step 3: Calculate the topology matching degree based on the preprocessed UAV flight data and 3D scene data; Step 4: Calculate the fusion weights of UAV flight data and 3D scene data based on the topology matching degree and the joint probability density association model; Step 5: Fuse the UAV flight data and 3D scene data according to the fusion weights, and visualize the fusion results.

2. The method for fusing multi-source heterogeneous data from UAVs based on a three-dimensional scene according to claim 1, characterized in that, The UAV flight data includes GPS latitude and longitude, altitude, flight speed, and sampling timestamp; The preprocessing of UAV flight data includes: data format standardization, handling of missing and outlier values, coordinate system unification, data resampling, and noise filtering.

3. The method for fusing multi-source heterogeneous data from UAVs based on a three-dimensional scene according to claim 2, characterized in that, The 3D scene data includes: terrain model, scene mesh, and texture map; The preprocessing of the 3D scene data includes: data lightweighting and redundancy removal, geometric error correction, coordinate and resolution unification, and invalid region masking. The preprocessed UAV flight data and the preprocessed 3D scene data are subjected to consistency verification.

4. The method for fusing multi-source heterogeneous data from UAVs based on a three-dimensional scene according to claim 3, characterized in that, The process of calculating the topology matching degree in step 3 includes: calculating the elevation difference and spatial overlap based on the preprocessed UAV flight data and 3D scene data, integrating the elevation difference and spatial overlap according to weights, and obtaining the final topology matching degree.

5. The method for fusing multi-source heterogeneous data from UAVs based on a three-dimensional scene according to claim 4, characterized in that, The process of calculating elevation difference includes: Spatial alignment: Using the coordinate system of the 3D scene data as a reference, the UAV flight data is mapped to the same coordinate system through coordinate transformation to ensure that the spatial positions of the two correspond. Sampling point selection: Select N sampling points at fixed intervals within the overlapping area of ​​the fused scene of UAV flight data and 3D scene data to cover the entire data area; Calculate elevation difference: Calculate the elevation difference of each point, and use the average elevation difference or the maximum elevation difference to characterize the overall vertical matching degree.

6. The method for fusing multi-source heterogeneous data from UAVs based on a three-dimensional scene according to claim 4, characterized in that, The process of calculating spatial overlap includes: Extracting the region boundary: Extracting the minimum bounding rectangle S of the flight trajectory from the UAV flight data. 无人机 Extract the corresponding effective scene boundary S from the 3D scene data 场景 ; Calculate the overlapping area and the total area: Use spatial geometry algorithms to calculate the intersection area S between the drone region and the 3D scene region. 重叠 Calculate the area S of the union of the two sets. 并集 =S 无人机 +S 场景 -S 重叠 ; Calculate spatial overlap: S 空间重叠度 =S 重叠 / S 并集 ; The topology matching degree is obtained by weighting the elevation difference and spatial overlap.

7. The method for fusing multi-source heterogeneous data from UAVs based on a three-dimensional scene according to claim 6, characterized in that, The calculation process for the fusion weights includes: The elevation difference and spatial overlap in the topological matching degree are extracted and used as constraints input into the joint probability density association model. Based on the mean, variance, and joint covariance of the observation errors of the preprocessed UAV flight data and 3D scene data, a joint probability density function of a two-dimensional normal distribution is constructed, and the initial probability density value of each spatial sampling point is calculated. The initial probability density value is weighted and corrected using the topological matching degree to enhance the probability contribution of high-matching data. The corrected probability density values ​​are normalized to obtain the fusion weights corresponding to each sampling point. The fusion weights range from [0, 1].

8. The method for fusing multi-source heterogeneous data from UAVs based on a three-dimensional scene according to claim 7, characterized in that, The expression for the joint probability density correlation model is: ； Where x represents the preprocessed UAV flight data observation at the target sampling point, y represents the preprocessed 3D scene data observation at the same target sampling point, f(x,y) is the joint probability density value of the two types of data at that sampling point; μ1 is the mean elevation error of the UAV flight data; σ1 2 σ² represents the elevation error variance of the UAV flight data; μ² represents the mean elevation error of the 3D scene data; σ² represents the mean elevation error of the UAV flight data. 2 ρ represents the elevation error variance of the 3D scene data; ρ represents the joint error covariance, which is determined by analyzing the error correlation between the two types of data in historical matching samples.

9. The method for fusing multi-source heterogeneous data from UAVs based on a three-dimensional scene according to claim 8, characterized in that, The formula for weighting and correcting the initial probability density value using the topological matching degree is as follows: F'(x,y)=f(x,y)×[0.5+0.5×M]; Where 0.5 is the basic weight coefficient, and 0.5×M is the contribution weight of topology matching degree; M is the topology matching degree.

10. A UAV multi-source heterogeneous data fusion system based on a 3D scene, characterized in that, include: Data acquisition module: Acquires drone flight data and 3D scene data; Preprocessing module: performs preprocessing on the UAV flight data and 3D scene data respectively; Topology matching degree calculation module: Calculates the topology matching degree based on the preprocessed UAV flight data and 3D scene data; Model calculation module: used to calculate the fusion weights of UAV flight data and 3D scene data based on the topological matching degree and the joint probability density association model; Visualization module: Used to fuse UAV flight data and 3D scene data according to fusion weights, and visualize the fusion results.

Images