A method for correcting high-precision mapping errors based on the flight state of an unmanned aerial vehicle

Abstract

The present invention discloses a method for correcting high-precision mapping errors based on the flight state of an unmanned aerial vehicle, which relates to the technical field of data error correction and includes: obtaining the mapping attitude data of the task flight path of the unmanned aerial vehicle in the area to be mapped, performing dynamic weight allocation according to the federated filter, and generating a spatio-temporal synchronization matrix of the task flight path in the mapping area of the unmanned aerial vehicle; establishing an exposure control-distortion compensation function according to the spatio-temporal synchronization matrix of the task flight path in the mapping area of the unmanned aerial vehicle, correcting the task initialization image parameters in the mapping area of the unmanned aerial vehicle, obtaining the task correction image parameters in the mapping area of the unmanned aerial vehicle, updating the optimal estimation of the mapping attitude data of the task flight path in the mapping area of the unmanned aerial vehicle, and performing iterative matching with the map point cloud in the mapping area to generate a high-precision image of the mapping area of the unmanned aerial vehicle. The advantages of the present invention are as follows: improving the mapping accuracy of the unmanned aerial vehicle, reducing error accumulation, and optimizing image quality.

Description

Technical Field

[0001] The present invention relates to the technical field of data error correction, and specifically relates to a method for correcting high-precision mapping errors based on the flight state of an unmanned aerial vehicle (UAV). Background Art

[0002] In existing high-precision UAV mapping, there is insufficient accuracy in flight state estimation, resulting in the continuous accumulation of mapping errors during long-term flights, affecting the accuracy of the final images and point cloud data. In complex terrains or environmental conditions, sensor errors and inaccurate attitude estimation will exacerbate the propagation of errors, leading to an increase in the deviation of the overall mapping results and making it difficult to meet high-precision requirements. Summary of the Invention

[0003] To solve the above technical problems, a method for correcting high-precision mapping errors based on the flight state of an unmanned aerial vehicle is provided. This technical solution solves the problems in existing high-precision UAV mapping, where there is insufficient accuracy in flight state estimation, resulting in the continuous accumulation of mapping errors during long-term flights, affecting the accuracy of the final images and point cloud data. In complex terrains or environmental conditions, sensor errors and inaccurate attitude estimation will exacerbate the propagation of errors, leading to an increase in the deviation of the overall mapping results and making it difficult to meet high-precision requirements.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] A method for correcting high-precision mapping errors based on the flight state of an unmanned aerial vehicle, comprising:

[0006] Based on the UAV mapping management background, determine the mission flight path of the UAV in the area to be mapped;

[0007] Based on heterogeneous sensors, obtain the mission flight path mapping attitude data of the UAV in the area to be mapped, mark the multi-source errors in the mission flight path mapping attitude data, and perform dynamic weight allocation according to the federated filter to generate the spatio-temporal synchronization matrix of the mission flight path in the mapping area of the UAV;

[0008] Based on the mission flight path mapping attitude data of the UAV in the mapping area, establish the mission initialization image parameters of the mapping area of the UAV;

[0009] According to the spatio-temporal synchronization matrix of the mission flight path in the mapping area of the UAV, establish an exposure control - distortion compensation function to correct the mission initialization image parameters of the mapping area of the UAV and obtain the mission corrected image parameters of the mapping area of the UAV;

[0010] Modify the image parameters according to the tasks of the mapping area of the UAV, update the optimal estimate of the mapping attitude data of the mission flight path in the mapping area of the UAV, and iteratively match with the map point cloud in the mapping area to generate a high-precision image of the mapping area of the UAV.

[0011] Preferably, based on heterogeneous sensors, obtain the mapping attitude data of the mission flight path in the area to be mapped by the UAV, mark the multi-source errors in the mapping attitude data of the mission flight path, and perform dynamic weight allocation according to the federated filter to generate the spatio-temporal synchronization matrix of the mission flight path in the mapping area of the UAV, which specifically includes:

[0012] Based on heterogeneous sensors, obtain the mapping attitude data of the mission flight path in the mapping area of the UAV for preprocessing; the mapping attitude data includes: IMU data, RTK-GNSS data, and point cloud data;

[0013] According to the federated filter architecture, for each type of mapping attitude data in the mapping attitude data of the mission flight path in the mapping area of the UAV, establish a sub-individual Kalman filter, generate a local optimal estimate and substitute it into the parent Kalman filter to obtain the optimal estimate value of the mapping attitude data of the mission flight path in the area to be mapped by the UAV;

[0014] According to the optimal estimate value of the mapping attitude data of the mission flight path in the mapping area of the UAV, align according to the timestamps of each data to form a time synchronization matrix;

[0015] According to the optimal estimate value of the mapping attitude data of the mission flight path in the mapping area of the UAV, convert the carrier coordinates of each data to the navigation coordinate system to establish a space transformation matrix;

[0016] Based on the time synchronization matrix and the space transformation matrix, establish a coordinate rotation correction-time delay compensation function to generate the spatio-temporal synchronization matrix of the mission flight path in the mapping area of the UAV;

[0017] ,

[0018] where, is the measurement position coordinate of the i-th mapping attitude data of the mission flight path in the mapping area of the UAV, is the acquisition timestamp of the i-th mapping attitude data of the mission flight path in the mapping area of the UAV, is the space transformation matrix, is the time synchronization matrix, is the measurement velocity vector of the UAV inertial measurement unit, is the time synchronization error of the UAV mapping attitude data, is the global coordinate position after spatio-temporal alignment of the i-th mapping attitude data of the mission flight path in the mapping area of the UAV, It is the timestamp after synchronization of the mapping attitude data of the i-th mission flight path in the mapping area of the UAV.

[0019] Preferably, an exposure control - distortion compensation function is established according to the spatio-temporal synchronization matrix of the mission flight path in the mapping area of the UAV, and the mission initialization image parameters in the mapping area of the UAV are corrected to obtain the mission corrected image parameters in the mapping area of the UAV, which specifically include:

[0020] Based on the spatio-temporal synchronization matrix of the mission flight path in the mapping area of the UAV, the illumination data and image data of the mission flight path in the mapping area of the UAV are marked per unit time;

[0021] Based on the illumination data of the mission flight path in the mapping area of the UAV, the point cloud reflectivity is associated with the visual RGB value, an AE illumination intensity distribution function is constructed, and the image illumination intensity distribution value of the mission flight path in the mapping area of the UAV is generated;

[0022] According to the image illumination intensity distribution value of the mission flight path in the mapping area of the UAV, substituting it into the illumination field model to generate the dynamic image brightness value of the mission flight path in the mapping area of the UAV;

[0023] Based on the CNN convolutional neural network, taking the original image data and IMU data of the mission flight path in the mapping area of the UAV as inputs, and taking the distortion compensation image data of the mission flight path in the mapping area of the UAV as the output;

[0024] Using the dynamic image brightness value of the mission flight path in the mapping area of the UAV and the distortion compensation image data of the mission flight path in the mapping area of the UAV to correct the mission initialization image parameters in the mapping area of the UAV, and obtaining the mission corrected image parameters in the mapping area of the UAV;

[0025] Among them, the dynamic image brightness value of the mission flight path in the mapping area of the UAV is specifically:

[0026] ,

[0027] In the formula, is the dynamic image brightness value of the i-th mission flight path in the mapping area of the UAV, is the illumination intensity fusion value of the image coordinate point of the i-th mission flight path in the mapping area of the UAV, is the visual RGB value of the image coordinate point of the i-th mission flight path in the mapping area of the UAV, is the point cloud reflectivity value of the image coordinate point of the i-th mission flight path in the mapping area of the UAV, is the visual RGB sensor weight coefficient, is the cloud reflectivity weight coefficient, is the area weight of the i-th mission flight path in the mapping area of the UAV, and N is the total number of mission flight paths in the mapping area of the UAV;

[0028] Among them, the distorted compensation image data of the mission flight path in the mapping area of the UAV is specifically: ,

[0029] In the formula, is the distorted compensation image data of the i-th mission flight path in the mapping area of the UAV, is the original image data of the i-th mission flight path in the mapping area of the UAV, is the IMU data of the i-th mission flight path in the mapping area of the UAV, is the attitude angle, is the CNN convolutional neural network interface function.

[0030] Preferably, according to the mission correction image parameters in the mapping area of the UAV, update the optimal estimate of the mapping attitude data of the mission flight path in the mapping area of the UAV, and perform iterative matching with the map point cloud in the mapping area to generate a high-precision image of the mapping area of the UAV specifically as follows;

[0031] Based on the mission correction image parameters in the mapping area of the UAV, use the Kalman filter update formula to update the optimal estimate of the mapping attitude data of the mission flight path in the mapping area of the UAV, and generate the optimal state estimate of the mapping attitude data of the mission flight path in the mapping area of the UAV;

[0032] Based on the optimal state estimate of the mapping attitude data of the mission flight path in the mapping area of the UAV and the map point cloud in the mapping area, perform iterative matching according to the ICP iterative closest point algorithm to generate a high-precision image of the mapping area of the UAV;

[0033] Among them, the specific Kalman filter update formula is: ,

[0034] In the formula, is the optimal state estimate of the i-th mission flight path in the mapping area of the UAV, is the optimal estimated value of the i-th mission flight path in the mapping area of the UAV, is the state transition matrix of the mapping attitude data of the mission flight path in the mapping area of the UAV, is the Kalman gain, is the original value of the mapping attitude data of the mission flight path in the mapping area of the UAV, is the observation matrix of the mapping attitude data of the mission flight path in the mapping area of the UAV.

[0035] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0036] The present invention proposes a scheme for correcting high-precision surveying and mapping errors based on the flight state of an unmanned aerial vehicle (UAV). It corrects surveying and mapping errors by using the flight state of the UAV, combines heterogeneous sensor data and federated filtering technology, and precisely corrects multi-source errors generated during the flight of the UAV. By dynamically adjusting the weights of flight path data, a spatio-temporal synchronization matrix is generated, and then the initial image parameters are established and corrected. An exposure control and distortion compensation model is used to optimize the image quality, and through iterative matching with map point clouds, high-precision complete image parameters are generated. The beneficial effects of this scheme are as follows: improving the surveying and mapping accuracy of the UAV, reducing error accumulation, and optimizing the image quality. Description of the Drawings

[0037] Figure 1 It is a flowchart of a method for correcting high-precision surveying and mapping errors based on the flight state of an unmanned aerial vehicle;

[0038] Figure 2 It is a flowchart of a method for generating a spatio-temporal synchronization matrix of the mission flight path of the surveying area of the unmanned aerial vehicle;

[0039] Figure 3 It is a flowchart of a method for obtaining the mission correction image parameters of the surveying area of the unmanned aerial vehicle;

[0040] Figure 4 It is a flowchart of a method for generating a high-precision image of the surveying area of the unmanned aerial vehicle. Detailed Embodiments

[0041] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations.

[0042] Referring to Figure 1 As shown, a method for correcting high-precision surveying and mapping errors based on the flight state of an unmanned aerial vehicle includes:

[0043] Based on the UAV surveying and mapping management background, determine the mission flight path of the area to be surveyed by the UAV;

[0044] Based on heterogeneous sensors, obtain the mission flight path surveying and mapping attitude data of the area to be surveyed by the UAV, mark the multi-source errors in the mission flight path surveying and mapping attitude data, and perform dynamic weight allocation according to federated filtering to generate a spatio-temporal synchronization matrix of the mission flight path of the surveying area of the UAV;

[0045] Based on the mission flight path surveying and mapping attitude data of the surveying area of the UAV, establish the mission initial image parameters of the surveying area of the UAV;

[0046] An exposure control - distortion compensation function is established based on the spatio - temporal synchronization matrix of the mission flight path in the mapping area of the UAV, the initial image parameters of the mission in the mapping area of the UAV are corrected, and the corrected image parameters of the mission in the mapping area of the UAV are obtained;

[0047] According to the corrected image parameters of the mission in the mapping area of the UAV, the optimal estimate of the mapping attitude data of the mission flight path in the mapping area of the UAV is updated, and iterative matching is performed with the map point cloud in the mapping area to generate a high - precision image of the mapping area of the UAV.

[0048] This solution uses the UAV flight state to correct mapping errors, combines heterogeneous sensor data and federated filtering technology to accurately correct multi - source errors generated during the UAV flight. By dynamically adjusting the weights of flight path data, a spatio - temporal synchronization matrix is generated, and then the initial image parameters are established and corrected. An exposure control and distortion compensation model is used to optimize the image quality, and through iterative matching with the map point cloud, complete high - precision image parameters are generated. The beneficial effects of this solution are: improving the mapping accuracy of the UAV, reducing error accumulation, and optimizing the image quality.

[0049] Refer to Figure 2 As shown, based on heterogeneous sensors, the mapping attitude data of the mission flight path in the area to be mapped by the UAV is obtained, the multi - source errors in the mapping attitude data of the mission flight path are marked, and dynamic weight allocation is performed according to federated filtering. The specific steps for generating the spatio - temporal synchronization matrix of the mission flight path in the mapping area of the UAV include:

[0050] Based on heterogeneous sensors, the mapping attitude data of the mission flight path in the mapping area of the UAV is pre - processed; the mapping attitude data includes: IMU data, RTK - GNSS data, and point cloud data;

[0051] According to the federated filtering architecture, for each type of mapping attitude data in the mapping attitude data of the mission flight path in the mapping area of the UAV, a sub - individual Kalman filter is established, and the local optimal estimate is generated and substituted into the parent Kalman filter to obtain the optimal estimate value of the mapping attitude data of the mission flight path in the area to be mapped by the UAV;

[0052] According to the optimal estimate value of the mapping attitude data of the mission flight path in the mapping area of the UAV, a time synchronization matrix is formed by aligning the timestamps of each data;

[0053] According to the optimal estimate value of the mapping attitude data of the mission flight path in the mapping area of the UAV, a space transformation matrix is established by converting the carrier coordinates of each data to the navigation coordinate system;

[0054] Based on the time synchronization matrix and the space transformation matrix, a coordinate rotation correction-time delay compensation function is established to generate a spatio-temporal synchronization matrix for the mission flight path of the mapping area of the UAV.

[0055] ,

[0056] Among them, is the measurement position coordinate of the i-th mission flight path mapping attitude data in the mapping area of the UAV, is the acquisition timestamp of the i-th mission flight path mapping attitude data in the mapping area of the UAV, is the space transformation matrix, is the time synchronization matrix, is the measurement velocity vector of the UAV inertial measurement unit, is the time synchronization error of the UAV mapping attitude data, is the global coordinate position after spatio-temporal alignment of the i-th mission flight path mapping attitude data in the mapping area of the UAV, is the timestamp after synchronization of the i-th mission flight path mapping attitude data in the mapping area of the UAV.

[0057] This solution is based on the data fusion of heterogeneous sensors, combined with technologies such as federated filtering and Kalman filtering, to optimize the attitude data of the UAV in the mission flight path of the mapping area. Through the efficient preprocessing and error marking of multi-source data (IMU, RTK-GNSS, point cloud, etc.), the weights of the data are dynamically adjusted, and the optimal flight path mapping attitude estimation value is generated. By establishing the time synchronization and space transformation matrices, this solution effectively eliminates the spatio-temporal differences between different sensors, realizes the high-precision fusion and synchronization of mapping data, and provides effective data support for high-precision mapping tasks.

[0058] Referring to Figure 3 as shown, an exposure control-distortion compensation function is established according to the spatio-temporal synchronization matrix of the mission flight path of the mapping area of the UAV to correct the task initialization image parameters of the mapping area of the UAV, and the task correction image parameters of the mapping area of the UAV are obtained, specifically including:

[0059] Based on the spatio-temporal synchronization matrix of the mission flight path of the mapping area of the UAV, the illumination data and image data of the mission flight path of the mapping area of the UAV are marked according to the unit time;

[0060] Based on the illumination data of the mission flight path of the mapping area of the UAV, the point cloud reflectivity is associated with the visual RGB value, an AE illumination intensity distribution function is constructed, and the image illumination intensity distribution value of the mission flight path of the mapping area of the UAV is generated;

[0061] Substitute the image illumination intensity distribution value of the mission flight path in the mapping area of the UAV into the illumination field model to generate the dynamic image brightness value of the mission flight path in the mapping area of the UAV;

[0062] Based on the CNN convolutional neural network, use the original image data and IMU data of the mission flight path in the mapping area of the UAV as inputs, and use the distortion compensation image data of the mission flight path in the mapping area of the UAV as the output;

[0063] Use the dynamic image brightness value of the mission flight path in the mapping area of the UAV and the distortion compensation image data of the mission flight path in the mapping area of the UAV to correct the task initialization image parameters of the mission in the mapping area of the UAV, and obtain the task correction image parameters of the mission in the mapping area of the UAV;

[0064] Among them, the dynamic image brightness value of the mission flight path in the mapping area of the UAV is specifically: ,

[0065] In the formula, is the dynamic image brightness value of the i-th mission flight path in the mapping area of the UAV, is the illumination intensity fusion value of the image coordinate point of the i-th mission flight path in the mapping area of the UAV, is the visual RGB value of the image coordinate point of the i-th mission flight path in the mapping area of the UAV, is the point cloud reflectivity value of the image coordinate point of the i-th mission flight path in the mapping area of the UAV, is the visual RGB sensor weight coefficient, is the cloud reflectivity weight coefficient, is the area weight of the i-th mission flight path in the mapping area of the UAV, and N is the total number of mission flight paths in the mapping area of the UAV;

[0066] Among them, the distortion compensation image data of the mission flight path in the mapping area of the UAV is specifically: ,

[0067] In the formula, is the distortion compensation image data of the i-th mission flight path in the mapping area of the UAV, is the original image data of the i-th mission flight path in the mapping area of the UAV, is the IMU data of the i-th mission flight path in the mapping area of the UAV, is the attitude angle, is the CNN convolutional neural network interface function.

[0068] It is understandable that the cloud reflectivity weight coefficient is dynamically updated through federated filtering to improve the data fusion accuracy.

[0069] By combining the spatio-temporal synchronization matrix of the mapping area mission flight path of the UAV and utilizing the correlation between illumination data and image data, this solution constructs an exposure control and distortion compensation model, which can effectively correct the image parameters of the UAV in the mapping mission. Through the generation of the illumination intensity distribution function and the dynamic image brightness value, combined with the distortion compensation training of the CNN convolutional neural network, this solution can eliminate the influence of illumination changes and image distortion on the image quality, thereby improving the accuracy and precision of the image, enhancing the reliability of the mapping data, and providing more accurate visual information support for subsequent mapping analysis.

[0070] Refer to Figure 4 As shown, according to the mission of the mapping area of the UAV to correct the image parameters, update the optimal estimate of the mapping attitude data of the mission flight path of the mapping area of the UAV, and perform iterative matching with the map point cloud of the mapping area to generate a high-precision image of the mapping area of the UAV specifically as follows;

[0071] Based on the mission of the mapping area of the UAV to correct the image parameters, use the Kalman filter update formula to update the optimal estimate of the mapping attitude data of the mission flight path of the mapping area of the UAV, and generate the optimal state estimate of the mapping attitude data of the mission flight path of the mapping area of the UAV;

[0072] Based on the optimal state estimate of the mapping attitude data of the mission flight path of the mapping area of the UAV and the map point cloud of the mapping area, perform iterative matching according to the ICP iterative closest point algorithm to generate a high-precision image of the mapping area of the UAV;

[0073] Among them, the specific Kalman filter update formula is: ,

[0074] In the formula, is the optimal state estimate of the i-th mission flight path of the mapping area of the UAV, is the optimal estimated value of the i-th mission flight path of the mapping area of the UAV, is the state transition matrix of the mapping attitude data of the mission flight path of the mapping area of the UAV, is the Kalman gain, is the original value of the mapping attitude data of the mission flight path of the mapping area of the UAV, is the observation matrix of the mapping attitude data of the mission flight path of the mapping area of the UAV.

[0075] The solution corrects image parameters by combining the mapping area task of the drone, uses Kalman filtering to update the optimal estimate of the flight path mapping attitude data, and precisely matches with the map point cloud of the mapping area through the ICP iterative closest point algorithm, thereby generating high-precision images. This method can effectively improve the accuracy of attitude estimation, precisely align the map point cloud and image data, eliminate flight path errors and image distortions, enhance the data accuracy and reliability in the drone mapping task, and support higher-quality mapping and map reconstruction.

[0076] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection required by the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for correcting high-precision mapping errors based on the flight status of an unmanned aerial vehicle, characterized in that: include: Based on the UAV mapping management background, determine the mission flight path of the UAV in the area to be mapped; Based on heterogeneous sensors, the mission flight path mapping attitude data of the UAV in the area to be mapped is obtained, the multi-source errors in the mission flight path mapping attitude data are marked, and dynamic weight allocation is performed according to the federated filter to generate the mission flight path time-space synchronization matrix of the UAV's mapping area; Based on the mission flight path mapping attitude data of the UAV's mapping area, establish the mission initialization image parameters of the UAV's mapping area; An exposure control-distortion compensation function is established according to the space-time synchronization matrix of the mission flight path of the UAV's surveying and mapping area, and the mission initialization image parameters of the UAV's surveying and mapping area are corrected to obtain the mission correction image parameters of the UAV's surveying and mapping area; According to the mission of the UAV's mapping area, the image parameters are corrected, the optimal estimate of the mission flight path mapping attitude data of the UAV's mapping area is updated, and iterative matching is performed with the map point cloud of the mapping area to generate a high-precision image of the UAV's mapping area.

2. According to claim 1, a method for correcting high-precision surveying and mapping errors based on the flight status of an unmanned aerial vehicle is characterized in that: Based on heterogeneous sensors, the task flight path mapping attitude data of the UAV in the area to be mapped is obtained, the multi-source errors in the task flight path mapping attitude data are marked, and dynamic weight allocation is performed according to the federated filter to generate the task flight path time-space synchronization matrix of the UAV mapping area. Specifically, it includes: Based on heterogeneous sensors, the mission flight path mapping attitude data of the UAV's mapping area is obtained for preprocessing; the mapping attitude data includes: IMU data, RTK-GNSS data, and point cloud data; According to the federated filtering architecture, a child individual Kalman filter is established based on each type of mapping attitude data in the mission flight path mapping attitude data of the mapping area of ​​the UAV, and a local optimal estimate is generated and substituted into the parent Kalman filter to obtain the optimal estimate of the mission flight path mapping attitude data of the UAV's mapping area. According to the optimal estimate of the attitude data of the mission flight path of the UAV's mapping area, the time synchronization matrix is ​​formed by aligning the timestamps of each data; According to the optimal estimate of the attitude data of the mission flight path of the UAV's mapping area, the carrier coordinates of each data are converted to the navigation coordinate system to establish a space conversion matrix; Based on the time synchronization matrix and the space conversion matrix, a coordinate rotation correction-time delay compensation function is established to generate the space-time synchronization matrix of the mission flight path of the UAV's mapping area; , in, The measured position coordinates of the mapping attitude data of the i-th mission flight path of the UAV’s mapping area, is the acquisition timestamp of the mapping attitude data of the flight path of the i-th mission in the mapping area of ​​the UAV, is the space transformation matrix, is the time synchronization matrix, is the measured velocity vector of the UAV inertial measurement unit, is the time synchronization error of the UAV mapping attitude data, is the global coordinate position of the i-th mission flight path mapping attitude data of the UAV's mapping area after time-space alignment, It is the timestamp after synchronization of the mapping attitude data of the flight path of the i-th mission in the mapping area of ​​the UAV.

3. The method for correcting high-precision surveying and mapping errors based on the flight status of an unmanned aerial vehicle according to claim 2 is characterized in that: According to the space-time synchronization matrix of the mission flight path of the UAV's surveying and mapping area, an exposure control-distortion compensation function is established to correct the mission initialization image parameters of the UAV's surveying and mapping area. The mission correction image parameters of the UAV's surveying and mapping area are obtained, which specifically include: Based on the spatiotemporal synchronization matrix of the mission flight path of the surveying and mapping area of ​​the UAV, the illumination data and image data of the mission flight path of the surveying and mapping area of ​​the UAV are marked according to the unit time; Based on the illumination data of the mission flight path of the UAV's surveying and mapping area, the AE illumination intensity distribution function is constructed by associating the point cloud reflectivity with the visual RGB value, and the image illumination intensity distribution value of the mission flight path of the UAV's surveying and mapping area is generated; Substituting the image illumination intensity distribution value of the mission flight path of the surveying and mapping area of ​​the UAV into the illumination field model, the dynamic image brightness value of the mission flight path of the surveying and mapping area of ​​the UAV is generated; Based on the CNN convolutional neural network, the original image data and IMU data of the mission flight path of the UAV's surveying area are used as input, and the distortion-compensated image data of the mission flight path of the UAV's surveying area is used as output; The dynamic image brightness value of the mission flight path of the UAV's surveying and mapping area and the distortion compensation image data of the mission flight path of the UAV's surveying and mapping area are used to correct the mission initialization image parameters of the UAV's surveying and mapping area to obtain the mission correction image parameters of the UAV's surveying and mapping area.

4. The method for correcting high-precision surveying and mapping errors based on the flight status of an unmanned aerial vehicle according to claim 3 is characterized in that: The dynamic image brightness value of the mission flight path of the surveying area of ​​the UAV is specifically: ， In the formula, is the dynamic image brightness value of the i-th mission flight path in the surveying area of ​​the UAV, is the illumination intensity fusion value of the image coordinate point of the i-th mission flight path in the surveying area of ​​the UAV, is the visual RGB value of the image coordinate point of the i-th mission flight path in the mapping area of ​​the UAV, is the point cloud reflectivity value of the image coordinate point of the i-th mission flight path in the surveying area of ​​the UAV, is the visual RGB sensor weight coefficient, is the cloud reflectivity weight coefficient, is the regional weight of the i-th mission flight path in the surveying area of ​​the UAV, and N is the total number of mission flight paths in the surveying area of ​​the UAV.

5. The method for correcting high-precision surveying and mapping errors based on the flight status of an unmanned aerial vehicle according to claim 4 is characterized in that: The distortion-compensated image data of the mission flight path of the surveying area of ​​the UAV is specifically: , In the formula, is the distortion-compensated image data of the flight path of the ith mission in the mapping area of ​​the UAV, is the original image data of the flight path of the ith mission in the surveying area of ​​the UAV, is the IMU data of the flight path of the i-th mission in the mapping area of ​​the UAV, is the attitude angle, It is the CNN convolutional neural network interface function.

6. The method for correcting high-precision surveying and mapping errors based on the flight status of an unmanned aerial vehicle according to claim 5 is characterized in that: According to the mission of the UAV's mapping area, the image parameters are corrected, the optimal estimate of the mapping attitude data of the mission flight path of the UAV's mapping area is updated, and iterative matching is performed with the map point cloud of the mapping area to generate a high-precision image of the UAV's mapping area. Specifically, it includes: Based on the mission correction image parameters of the UAV's mapping area, the Kalman filter update formula is used to update the optimal estimate of the mission flight path mapping attitude data of the UAV's mapping area, and the optimal state estimate of the mission flight path mapping attitude data of the UAV's mapping area is generated; Based on the optimal state estimation of the mapping posture data of the mission flight path of the UAV's mapping area and the map point cloud of the mapping area, iterative matching is performed according to the ICP iterative closest point algorithm to generate a high-precision image of the UAV's mapping area.

7. The method for correcting high-precision surveying and mapping errors based on the flight status of an unmanned aerial vehicle according to claim 6 is characterized in that: The update formula of the Mann filter is specifically: , In the formula, is the optimal state estimate of the flight path of the ith mission in the mapping area of ​​the UAV, is the optimal estimate of the flight path of the ith mission in the mapping area of ​​the UAV, The state transfer matrix of the attitude data for the mission flight path mapping of the UAV's mapping area, is the Kalman gain, The original value of the mission flight path mapping attitude data for the UAV's mapping area, An observation matrix of attitude data for the mission flight path of the UAV mapping area.

Images