Unmanned aerial vehicle photogrammetry supervision system and supervision method

Abstract

The invention relates to the technical field of unmanned aerial vehicle photogrammetry, in particular to an unmanned aerial vehicle photogrammetry supervision system and method. According to the method, the exposure, contrast, distortion and definition of the image shot by the unmanned aerial vehicle are comprehensively checked, and the image quality is ensured to meet the high standard of photogrammetry; according to the invention, distortion correction is carried out on the image by combining the distortion coefficient obtained by distortion inspection, so that measurement errors caused by image quality problems can be reduced, and the accuracy and reliability of measurement results can be improved; position parameters and environment parameters of the unmanned aerial vehicle are comprehensively analyzed, potential flight safety hazards are recognized in time, and flight accidents are avoided; according to output signals of the image quality detection module and the environment analysis module, image quality supervision and unmanned aerial vehicle safety supervision are automatically carried out, and the efficiency and safety of unmanned aerial vehicle photogrammetry are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of UAV photogrammetry, and specifically to a UAV photogrammetry supervision system and a supervision method. Background Art

[0002] In recent years, UAV photogrammetry technology has been widely applied in many fields such as geographic information collection, environmental monitoring, urban planning, and disaster assessment. Through the high-resolution cameras and other sensors carried by UAVs, this technology can quickly and efficiently obtain surface information, providing important data support for research and decision-making in related fields. However, there are still some problems and deficiencies in the actual application of current UAV photogrammetry technology:

[0003] Firstly, when a UAV flies in a complex and changeable environment, due to factors such as lighting conditions, improper camera parameter settings, and lens distortion, the captured images often have quality problems such as overexposure, underexposure, abnormal contrast, and blurred images. These problems will directly affect the accuracy and reliability of subsequent photogrammetry.

[0004] Secondly, when a UAV performs a photogrammetry task, it may encounter safety hazards such as bad weather and abnormal flight parameters. These factors not only threaten the flight safety of the UAV but also may affect the quality and efficiency of image acquisition.

[0005] Finally, traditional UAV photogrammetry operations often require manual monitoring of flight parameters and image quality, which not only increases labor costs but also makes it difficult to achieve real-time monitoring and timely adjustment. Therefore, it is particularly important to develop a system that can automatically supervise the UAV photogrammetry process and flight safety.

[0006] In view of the above problems, it is necessary to propose a UAV photogrammetry supervision system and a supervision method. Summary of the Invention

[0007] The purpose of the present invention is to solve the problems existing in the background art and to propose a UAV photogrammetry supervision system and a supervision method.

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] A UAV photogrammetry supervision system and a supervision method;

[0010] In the first aspect, the present invention provides a UAV photogrammetry supervision system, including a data acquisition module, an image quality detection module, a photogrammetry registration module, an environmental analysis module, and a feedback execution module.

[0011] The data acquisition module is responsible for collecting UAV position parameters, image data, and environmental parameters through the sensors and cameras carried by the UAV.

[0012] The specific process of collecting the UAV position parameters is as follows:

[0013] Access the global navigation satellite system to obtain the position parameters of the location where the UAV is located, including the latitude, longitude, and altitude of the location where the UAV is located. Access the inertial measurement unit to obtain the speed and acceleration of the UAV in the east-west direction, north-south direction, and vertical direction;

[0014] Calculate the pitch angle and roll angle of the UAV flight through the acceleration of the UAV in the east-west direction, north-south direction, and vertical direction.

[0015] The specific process of collecting the UAV image data is as follows:

[0016] Access the images taken by the UAV through the camera to obtain the height and width of each image; obtain the pixel coordinates, pixel brightness, and pixel values of all pixels in each image.

[0017] The specific process of collecting the UAV environmental parameters is as follows:

[0018] Obtain the maximum visibility, air pressure, wind speed, and temperature of the location where the UAV is located.

[0019] Send the UAV image data to the image quality detection module; send the UAV position parameters and environmental parameters to the environmental analysis module;

[0020] The image quality detection module obtains the UAV image data, performs image quality detection through exposure check, contrast check, distortion check, and sharpness check, and performs data fusion on the detection results to analyze the image quality problems occurring in the photogrammetry process.

[0021] The specific process of the exposure check is as follows:

[0022] Calculate the average exposure of each image through the operation of pixel coordinates and pixel brightness.

[0023] The specific process of the contrast check is as follows:

[0024] Calculate the contrast of each image through the operation of pixel coordinates, pixel brightness, and the average exposure of each image.

[0025] The specific process of the distortion check is as follows:

[0026] As a preferred embodiment of the present invention, establish a radial distortion model by combining the pixel distance after radial distortion, the pixel distance when there is no radial distortion ideally, and the radial distortion coefficient:

[0027] As a preferred embodiment of the present invention, a tangential distortion model is established by combining the pixel coordinates after tangential distortion, the pixel coordinates in the ideal state without tangential distortion, and the tangential distortion coefficients:

[0028] As a preferred embodiment of the present invention, image recognition algorithms are used to locate each known landmark reference point in each image, and the corresponding actual world coordinates and pixel coordinates in the image of each known landmark reference point are obtained;

[0029] By calculating the actual world coordinates corresponding to each known landmark reference point, the speculated pixel coordinates of each known landmark reference point in each image are obtained.

[0030] As a preferred embodiment of the present invention, the pixel distances after radial distortion are calculated through the pixel coordinates of each known landmark reference point in the image; the pixel distances in the ideal state without radial distortion are calculated through the speculated pixel coordinates of each known landmark reference point; and the calculated pixel distances after radial distortion and the pixel distances in the ideal state without radial distortion are input into the radial distortion model. For each known landmark reference point in each image, an equation with the distortion function as the independent variable is generated; a system of simultaneous equations is established to solve for the radial distortion coefficients;

[0031] As a preferred embodiment of the present invention, the pixel coordinates of each known landmark reference point in the image are input into the tangential distortion model as the pixel coordinates after tangential distortion; the speculated pixel coordinates of each known landmark reference point are input into the tangential distortion model as the pixel coordinates in the ideal state without tangential distortion; for each known landmark reference point in each image, an equation with the tangential distortion function as the independent variable is generated, a system of simultaneous equations is established, and the tangential distortion coefficients are solved.

[0032] The specific process of sharpness inspection is as follows:

[0033] As a preferred embodiment of the present invention, the horizontal gradients and vertical gradients of each image at all pixel coordinates in the image are calculated through operations on the pixel values; the average gradient magnitude of each image is obtained through operations on the horizontal gradients and vertical gradients of each image at all pixel coordinates in the image.

[0034] The radial distortion coefficients and tangential distortion coefficients obtained by distortion inspection of the images taken by the drone are sent to the photogrammetric registration module; the average exposure, contrast, and average gradient magnitude obtained by exposure inspection, contrast detection, and sharpness inspection of the images taken by the drone are sent to the image quality detection module.

[0035] The image quality detection module obtains the average exposure, contrast, and average gradient magnitude of each image and conducts image quality supervision on all images.

[0036] As a preferred embodiment of the present invention, the following numerical judgments are made on the average exposure, contrast, and average gradient magnitude generated from the same image:

[0037] If the average exposure of the image is greater than the maximum threshold, it is determined that the overall exposure of the image is too strong, resulting in the loss of image details, and an overexposure signal corresponding to the image is output; if the average exposure of the image is less than the minimum threshold, it is determined that the overall illumination of the image is too weak, resulting in the inability to identify the image area, and an underexposure signal of the image is output.

[0038] If the contrast of the image is greater than the maximum threshold, it is determined that the details of the image are overly exaggerated, resulting in overly extreme colors, and a high-contrast signal is output; if the contrast of the image is less than the minimum threshold, it is determined that the image lacks details and levels and effective photogrammetric information cannot be extracted from it, and a low-contrast signal is output.

[0039] If the average gradient magnitude of the image is lower than the minimum threshold, it is determined that the image is overly blurred and the details cannot be distinguished, and a blur signal is generated.

[0040] All the generated signals are output to the photogrammetric registration module and the feedback execution module.

[0041] The photogrammetric registration module performs photogrammetric registration according to the radial distortion coefficient and tangential distortion coefficient obtained from the distortion inspection.

[0042] Extract all the images that have not generated overexposure signals, underexposure signals, high-contrast signals, low-contrast signals, and blur signals, and mark them as feature images.

[0043] Perform distortion correction on all the feature images, extract the radial distortion coefficient and inversely input it into the radial distortion model; extract the tangential distortion coefficient and inversely input it into the tangential distortion model, and establish a system of simultaneous equations to solve the true values of all pixel coordinates in each image.

[0044] Perform image registration. Extract the coordinates of each known landmark reference point after image distortion correction from each feature image as the feature points of each feature image. Use the known landmark reference points with the same identifier as the anchor points for feature image stitching. Stitch the same known landmark reference point j in each feature image to obtain the image registration result.

[0045] The environmental analysis module calculates and analyzes the collected UAV position parameters and environmental parameters to identify potential flight safety hazards;

[0046] Perform a comprehensive analysis of the UAV position parameters. The specific process is as follows:

[0047] Obtain the latitude, longitude, and altitude of the UAV's location and the latitude, longitude, and altitude of the target flight location, and calculate the target position deviation eigenvalue through operations;

[0048] Obtain the UAV's current speeds in the east-west direction, north-south direction, and vertical direction, and calculate the speed overlimit eigenvalue through operations;

[0049] Obtain the pitch angle and roll angle of the UAV, and calculate the attitude anomaly eigenvalue through operations;

[0050] Calculate the flight safety hazard index through operations on the target position deviation eigenvalue, speed overlimit eigenvalue, and attitude anomaly eigenvalue; if the flight safety hazard index is greater than the preset threshold, output the first flight safety warning signal.

[0051] Conduct a comprehensive analysis of the UAV's environmental parameters. The specific process is as follows: Obtain the maximum visibility, air pressure, wind speed, and temperature at the UAV's location;

[0052] Calculate the visibility overlimit eigenvalue through operations on the maximum visibility at the UAV's location;

[0053] Calculate the air pressure overlimit eigenvalue through operations on the air pressure at the UAV's location;

[0054] Calculate the wind speed overlimit eigenvalue through operations on the wind speed at the UAV's location;

[0055] Calculate the temperature overlimit eigenvalue through operations on the temperature at the UAV's location;

[0056] Calculate the environmental safety hazard index through operations on the UAV's visibility overlimit eigenvalue, air pressure overlimit eigenvalue, wind speed overlimit eigenvalue, and temperature overlimit eigenvalue.

[0057] If the environmental safety hazard index is greater than the preset threshold, output the second flight safety warning signal.

[0058] Output all the generated signals to the feedback execution module;

[0059] The feedback execution module conducts image quality supervision by analyzing the signals output by the image quality detection module of the analysis and processing module; conducts UAV safety supervision by analyzing the signals output by the environmental analysis module.

[0060] The specific process of conducting image quality supervision is as follows:

[0061] Obtain all overexposure signals, underexposure signals, high-contrast signals, low-contrast signals, and blur signals, and count the number of times they occur.

[0062] If the number of overexposure signal generations is greater than a preset threshold, increase the shutter speed of the camera by a preset first adjustment base number and decrease the ISO value of the camera by a preset second adjustment base number;

[0063] If the number of underexposure signal generations is greater than a preset threshold, decrease the shutter speed of the camera by a preset first adjustment base number and increase the ISO value of the camera by a preset second adjustment base number;

[0064] If the number of high-contrast signal generations is greater than a preset threshold, prompt the user to adjust the shooting angle of the drone to avoid strong direct light sources;

[0065] If the number of low-contrast signal generations is greater than a preset threshold, prompt the user to adjust the shooting angle of the drone to enhance the light source intensity within the field of view of the drone camera;

[0066] If the number of blur signal generations is greater than a preset threshold, decrease the flight speed of the drone by a preset third adjustment base number, increase the flight stability of the drone, and reduce image blurring caused by vibration during the flight of the drone.

[0067] The specific process of drone safety supervision is as follows:

[0068] If the first flight safety warning signal is recognized, prompt the user to pay attention to the flight parameters of the drone;

[0069] For the second flight safety warning signal, prompt the user to note that the environment where the drone is located cannot meet the requirements of photogrammetry.

[0070] On the second aspect, the present invention provides a drone photogrammetry supervision method, including the following steps:

[0071] Step 1: Data collection;

[0072] The drone obtains position and motion data through the Global Navigation Satellite System and the Inertial Measurement Unit, including drone position parameters, velocity vectors, and acceleration vectors. Based on the drone position parameters, velocity vectors, and acceleration, the flight pitch angle and roll angle of the drone are obtained through analysis and calculation.

[0073] Image data is obtained through the camera, and the width, height (Hi), pixel brightness, and pixel values of each image are obtained. The environmental parameters include visibility, air pressure, wind speed, and temperature.

[0074] Step 2: Image quality monitoring;

[0075] Check the exposure, contrast, distortion, and sharpness of the images collected by the drone. Based on the brightness values and pixel coordinates of the images, the average exposure, contrast, distortion coefficient, and sharpness gradient values of each image are obtained through analysis and calculation.

[0076] As a preferred embodiment of the present invention, a radial distortion model and a tangential distortion model are established. Through an image recognition algorithm, landmark reference points are located, and distortion coefficient calculations are performed to obtain radial distortion coefficients and tangential distortion coefficients.

[0077] Step Three: Distortion correction and photogrammetric registration;

[0078] According to the inspection results of exposure, contrast, distortion, and sharpness, a quality detection feature vector for each image is generated. Based on the image quality feature vector of each image, the image quality detection results and distortion correction results are transmitted to the photogrammetric registration module through data fusion.

[0079] Photogrammetric registration is performed according to the calculation results of the distortion coefficients.

[0080] Extract all images that have not generated overexposure signals, underexposure signals, high-contrast signals, low-contrast signals, and blurred signals, and mark them as feature images.

[0081] Perform distortion correction on all feature images. Reverse input the distortion coefficients into the radial distortion model and the tangential distortion model, establish a system of simultaneous equations, and solve for the true values of all pixel coordinates in each image.

[0082] Perform image registration. Extract the coordinates of known landmark reference points after image distortion correction from each feature image as the feature points of each feature image. Use the known landmark reference points with the same identifier as the anchor points for feature image stitching. Stitch the same known landmark reference points in each feature image to obtain the image registration result.

[0083] Step Four: Environmental safety analysis;

[0084] Calculate and analyze the position parameters and environmental parameters of the drone. Based on the target position deviation, flight speed, and attitude anomaly characteristics of the flight path, obtain the flight safety hazard index through analysis and calculation; and obtain the environmental safety hazard index through analysis and calculation based on the environmental parameters. If these two indices exceed the set thresholds, flight safety warning and environmental safety warning signals are triggered respectively.

[0085] Step Five: Image quality analysis and optimization;

[0086] According to the signals output by the image quality detection module, count the occurrence times N1, N2, N3, N4, and N5 of overexposure, underexposure, high-contrast, low-contrast, and blurred signals. If the occurrence times of a certain signal exceed the preset threshold, corresponding adjustment measures are taken according to the type of detected signal:

[0087] If the overexposure signal N1 exceeds the threshold, adjust the shutter speed and ISO value of the camera;

[0088] If the underexposure signal N2 exceeds the threshold, increase the ISO and adjust the shutter speed;

[0089] If the high-contrast signal N3 exceeds the threshold, prompt to adjust the shooting angle;

[0090] If the low-contrast signal N4 exceeds the threshold, enhance the light source intensity;

[0091] If the blur signal N5 exceeds the threshold, reduce the flight speed and enhance the stability.

[0092] Step Six: Safety Warning and Execution Feedback;

[0093] According to the environmental analysis module and the results of image quality supervision, the feedback execution module makes corresponding feedback based on the flight safety warning signal and the environmental safety warning signal. If it is detected that the flight safety hazard exceeds the threshold, remind the user to adjust the flight parameters; if the environmental conditions do not meet the requirements of photogrammetry, prompt the user that the environment cannot meet the requirements and the flight route needs to be adjusted or environmental compensation needs to be carried out.

[0094] Compared with the prior art, the beneficial effects of the present invention are:

[0095] 1. The present invention comprehensively checks the exposure, contrast, distortion, and clarity of the images taken by the drone through the image quality detection module to ensure that the image quality meets the high standards of photogrammetry. Moreover, the present invention corrects the distortion of the images by combining the distortion coefficients obtained from the distortion inspection, which helps to reduce the measurement errors caused by image quality problems and improve the accuracy and reliability of the measurement results;

[0096] 2. The present invention comprehensively analyzes the position parameters (such as latitude, longitude, altitude, speed, acceleration, pitch angle, and roll angle) and environmental parameters (such as visibility, air pressure, wind speed, and temperature) of the drone, and timely identifies potential flight safety hazards. When the flight safety hazard index or the environmental safety hazard index exceeds the preset threshold, the system will issue a flight safety warning or an environmental safety warning signal to remind the user to take corresponding safety measures, thus effectively avoiding flight accidents;

[0097] 3. The present invention automatically conducts image quality supervision and drone safety supervision according to the output signals of the image quality detection module and the environmental analysis module. When image quality problems or flight safety hazards are detected, the system will automatically take corresponding adjustment measures, such as adjusting the shutter speed and ISO value of the camera, prompting the user to adjust the shooting angle or flight parameters, etc., to achieve intelligent supervision and adjustment and improve the efficiency and safety of drone photogrammetry. Description of the Drawings

[0098] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings:

[0099] Figure 1 It is the system block diagram of the present invention;

[0100] Figure 2 It is the schematic diagram of the radial distortion model of the present invention;

[0101] Figure 3 It is the schematic diagram of the tangential distortion model of the present invention;

[0102] Figure 4 It is the method flow chart of the present invention. Specific embodiments

[0103] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0104] Please refer to Figure 1 As shown, an unmanned aerial vehicle (UAV) photogrammetry supervision system includes a data acquisition module, an image quality detection module, a photogrammetry registration module, an environmental analysis module, and a feedback execution module.

[0105] The data acquisition module is responsible for collecting UAV position parameters, image data, and environmental parameters through sensors and cameras carried by the UAV.

[0106] The specific process of collecting UAV position parameters is as follows:

[0107] Access the Global Navigation Satellite System (GNSS) to obtain the position parameters (Lat, Lon, Alt) of the UAV's location, where Lat is the latitude of the UAV's location; Lon is the longitude of the UAV's location; Alt is the altitude of the UAV's location. Access the Inertial Measurement Unit (IMU) to obtain the velocity vx of the UAV in the east-west direction, the velocity vy in the north-south direction, and the velocity vz in the vertical direction; obtain the acceleration ax of the UAV in the east-west direction, the acceleration ay in the north-south direction, and the acceleration az in the vertical direction. Calculate the pitch angle θ1 and roll angle θ2 of the UAV's flight through a preset formula where g is the acceleration due to gravity. Denote the position parameters (Lat, Lon, Alt) of the UAV's location, the velocity vector (vx, vy, vz) of the UAV, the pitch angle θ1, and the roll angle θ2 as the UAV position parameters.

[0108] The specific process of collecting UAV image data is as follows:

[0109] Access the images captured by the drone through the camera, and obtain the image width Wi and image height Hi of each image i. Obtain the brightness Li(x, y) and pixel value Si(x, y) of each image i at the pixel coordinates (x, y). Where i is the serial number of the images captured by the drone through the camera, and i = 1, 2,..., n; n is the total number of images; where x is the pixel coordinate along the width direction; y is the pixel coordinate along the image height direction.

[0110] The specific process of collecting the drone environmental parameters is as follows:

[0111] Obtain the maximum visibility U, air pressure P, wind speed T, and temperature C at the location where the drone is located.

[0112] Furthermore, send the drone image data to the image quality detection module; send the drone position parameters and environmental parameters to the environmental analysis module;

[0113] The image quality detection module obtains the drone image data, performs image quality detection through exposure check, contrast check, distortion check, and clarity check, and performs data fusion on the detection results to analyze the image quality problems occurring in the photogrammetry process.

[0114] The specific process of the exposure check is as follows:

[0115] Through a preset formula Calculate the average exposure of image i Traverse all image serial numbers i in the calculation process of the average exposure to obtain the average exposure of each image.

[0116] The specific process of the contrast check is as follows:

[0117] Obtain the average exposure of each image. Through a preset formula Calculate the contrast of each image i

[0118] The specific process of the distortion check is as follows:

[0119] Please refer to Figure 2 as shown, establish a radial distortion model:

[0120] where r distorted is the pixel distance after radial distortion, r ideal is the pixel distance in the ideal case without radial distortion; where α1, α2, and α3 are the radial distortion coefficients to be obtained;

[0121] Please refer to Figure 3 as shown, establish a tangential distortion model:

[0122] where x distorted and y distorted are the pixel coordinates after tangential distortion; where x ideal and y ideal are the pixel coordinates in the ideal state without tangential distortion. Among them, β1 and β2 are the tangential distortion coefficients to be obtained.

[0123] Locate the known landmark reference points in each image i through the image recognition algorithm, and obtain their actual world coordinates (xj, yj, zj), where j is the numbering symbol of the known landmark reference point, j = 1, 2,..., m;

[0124] Through the preset camera calibration formula Calculate the estimated pixel coordinates (xj^, yj^) of the known landmark reference points in each image i. Among them, K is the internal parameter matrix of the camera; R and T are the rotation matrix and translation vector of the camera respectively.

[0125] Extract the actual world coordinates (xj, yj, zj) = (x1, y1, z1), (x2, y2, z2),..., (xm, ym, zm) of all known landmark reference points j; extract the estimated pixel coordinates (xj^, yj^) = (x1^, y1^), (x2^, y2^),..., (xm^, ym^) of all known landmark reference points j in each image i.

[0126] Furthermore, for each image i, take the distance in the estimated pixel coordinates of each known landmark reference point j in each image i as the pixel distance r in the ideal case without radial distortion ideal and input it into the radial distortion model; where j1 and j2 are the numbering symbols of the known landmark reference points included in image i, where j1 ∈ j and j2 belongs to j; take the actual distance between the known landmark reference points j1 and j2 in image i as the pixel distance r after radial distortion distorted and input it into the radial distortion model; establish a system of simultaneous equations, and solve the radial distortion coefficients α1, α2, and α3 through the nonlinear least squares method.

[0127] Furthermore, for each image i, take the estimated pixel coordinates (xj^, yj^) of all the known landmark reference points j included in it as the pixel coordinates x ideal and y ideal in the ideal state without tangential distortion and input them into the tangential distortion model; take the actual coordinates (xj, yj) of each known landmark reference point j in image i as the pixel coordinates x distorted and y distortedInput tangential distortion model; establish a system of simultaneous equations and solve for the tangential distortion coefficients β1 and β2 through nonlinear least squares method.

[0128] It should be noted that during the use of the UAV, environmental factors such as temperature, humidity, air pressure, and vibration will affect the optical characteristics of the camera, resulting in the distortion of the geometric shape of the captured images. Generally, this error is not very significant, but as the usage time increases, the distortion changes may gradually accumulate, affecting the positioning accuracy. In the UAV photogrammetry system, distortion inspection is very important for ensuring the accuracy of the images and the accuracy of subsequent image registration. The goal of distortion inspection is to ensure that the UAV obtains real image data by detecting whether there is excessive radial distortion and tangential distortion.

[0129] It should be further noted that in the solution results, the radial distortion coefficients α1, α2, and α3 are proportional to the severity of the radial distortion, that is, the larger the radial distortion coefficients, the more severe the radial distortion; the tangential distortion coefficients β1 and β2 are proportional to the severity of the tangential distortion, that is, the larger the tangential distortion coefficients, the more severe the tangential distortion.

[0130] The specific process of sharpness inspection is as follows:

[0131] Calculate the horizontal gradient Gi of image i at pixel coordinates (x, y) through a preset formula x (x, y) and the vertical gradient Gi y (x, y). Among them, Si(x + k1, y + k2) is the pixel value of image i at pixel coordinates (x + k1, y + k2); where k1 is the horizontal window; k2 is the vertical window, representing the range of gradient calculation; where Sobel x (k1, k2) is the horizontal direction filter of the Sobel operator, and where Sobel y (k1, k2) is the vertical direction filter of the Sobel operator, and

[0132] It should be noted that the horizontal gradient and the vertical gradient are local sharpness metrics of the image along different directions near the pixel point. Specifically, the horizontal gradient Gi x (x, y) represents the rate of change of the pixel values of image i along the width direction at pixel coordinates (x, y), and the higher its value, the greater the differentiation of the pixel values of image i along the height direction near pixel coordinates (x, y); the vertical gradient Gi y(x, y) represents the rate of change of the pixel value of image i in the height direction at pixel coordinates (x, y). The higher the value, the greater the differentiation of the pixel values of image i in the height direction near pixel coordinates (x, y). The greater the values of the horizontal gradient and the vertical gradient, the higher the local sharpness at the corresponding pixel coordinate positions.

[0133] Through a preset formula calculate the comprehensive gradient magnitude Gi of image i at pixel coordinates (x, y) mag (x, y);

[0134] Through a preset formula calculate the average gradient magnitude Gi of image i.

[0135] It should be noted that the average gradient magnitude is a measure of the overall sharpness of the image. The greater the average gradient magnitude, the clearer the overall image.

[0136] Furthermore, perform data fusion on the results of exposure check, contrast check, distortion check, and sharpness check. The specific process is as follows:

[0137] Generate the image quality detection feature vector of each image i ( Gi); generate the distortion check result feature vector of the drone (α1, α2, α3, β1, β2).

[0138] Send the distortion check result feature vector of the drone to the photogrammetric registration module; send the image quality detection feature vector to the image quality detection module.

[0139] The image quality detection module obtains the image quality detection feature vector of each image i ( Gi) and conducts image quality supervision.

[0140] If the average exposure of image i is greater than the maximum threshold Lmax, it is determined that the overall exposure of image i is too strong, resulting in the loss of image details, and an overexposure signal of image i is output; if the average exposure of image i is less than the minimum threshold Lmin, it is determined that the overall illumination of image i is too weak, resulting in the inability to identify the image area, and an underexposure signal of image i is output;

[0141] If the contrast of image i is greater than the maximum threshold Cmax, it is determined that the image details of image i are overly exaggerated, resulting in overly extreme colors, and a high-contrast signal is output; if the contrast of image i is less than the minimum threshold Cmin, it is determined that the image lacks details and levels and effective photogrammetric information cannot be extracted from it, and a low-contrast signal is output;

[0142] If the average gradient magnitude Gi of the image i is lower than the minimum threshold Gmin, it is determined that the image is overly blurred and the details therein cannot be distinguished, generating a blur signal.

[0143] Output all the generated signals to the photogrammetric registration module and the feedback execution module.

[0144] The photogrammetric registration module performs photogrammetric registration based on the feature vector (α1, α2, α3, β1, β2) of the distortion inspection result.

[0145] Extract all the images that have not generated overexposure signals, underexposure signals, high-contrast signals, low-contrast signals, and blur signals, and mark them as feature images.

[0146] Perform distortion correction on all the feature images, extract the radial distortion coefficients α1, α2, and α3, and inversely input them into the radial distortion model Extract the tangential distortion coefficients β1 and β2 and inversely input them into the tangential distortion model: Let Establish a system of simultaneous equations to solve the true values of all pixel coordinates (x, y) in each image i. Among them and are the squares of the coordinate differences of any two pixel coordinates along the width and height directions.

[0147] Perform image registration. Extract the coordinates of the known landmark reference points j after image distortion correction in each feature image as the feature points of each feature image. Use the known landmark reference points j with the same identifier as the anchor points for feature image stitching. Stitch the same known landmark reference points j in each feature image to obtain the image registration result.

[0148] The environmental analysis module calculates and analyzes the collected UAV position parameters and environmental parameters to identify potential flight safety hazards;

[0149] Perform a comprehensive analysis of the UAV position parameters. The specific process is as follows:

[0150] Obtain the position parameters (Lat, Lon, Alt) of the UAV's location and the target flight position (Lat_t, Lon_t, Alt_t). Through a preset formula Calculate the target position deviation eigenvalue f path ;

[0151] Obtain the UAV velocity vector (vx, vy, vz). Through a preset formula Calculate the speed overlimit eigenvalue f velocity ; where vmax is the preset maximum allowable speed.

[0152] Obtain the pitch angle θ1 and roll angle θ2 of the drone, and calculate the attitude anomaly eigenvalue f through the preset formula f attitude =max[(θ1 - θ1max), 0] + max[(θ2 - θ2max), 0]; where θ1max is the preset maximum safe pitch angle threshold, and θ2max is the preset maximum safe roll angle threshold. attitude ; where θ1max is the preset maximum safe pitch angle threshold, and θ2max is the preset maximum safe roll angle threshold.

[0153] Furthermore, calculate the flight safety hazard index S1 through the preset formula s1 = w1×f path + w2×f velocity + w3×f attitude ; where w1, w2, and w3 are preset weight factors.

[0154] If the flight safety hazard index S1 is greater than the preset threshold S1max, output the first flight safety warning signal.

[0155] Conduct a comprehensive analysis of the drone environmental parameters. The specific process is as follows:

[0156] Calculate the visibility overrun eigenvalue f through the preset formula visibility , the air pressure overrun eigenvalue f pressure , the wind speed overrun eigenvalue f wind and the temperature overrun eigenvalue f temperature ; where Umin is the minimum visibility threshold for photogrammetry, Umax is the maximum visibility threshold for photogrammetry; where Pmax is the maximum pressure threshold for photogrammetry, where Tmax is the maximum wind speed threshold for photogrammetry; and C ideal is the optimal ideal temperature for photogrammetry.

[0157] Calculate the environmental safety hazard index S2 through the preset formula S2 = w4×f visibility + w5×f pressure + w6×f wind + w7×f temperature ; where w4, w5, w6, and w7 are preset weight factors.

[0158] If the environmental safety hazard index S2 is greater than the preset threshold S2max, output the second flight safety warning signal.

[0159] Output all the generated signals to the feedback execution module;

[0160] The feedback execution module conducts image quality supervision by analyzing the signals output by the image quality detection module of the analysis processing module; conducts drone safety supervision by analyzing the signals output by the environmental analysis module.

[0161] The specific process of image quality supervision is as follows: Obtain all overexposure signals, underexposure signals, high-contrast signals, low-contrast signals, and blur signals, and count their occurrence times N1, N2, N3, N4, and N5.

[0162] If N1 is greater than the preset threshold, increase the shutter speed of the camera by a preset first adjustment base number, and decrease the ISO value of the camera by a preset second adjustment base number;

[0163] If N2 is greater than the preset threshold, decrease the shutter speed of the camera by a preset first adjustment base number, and increase the ISO value of the camera by a preset second adjustment base number;

[0164] If N3 is greater than the preset threshold, prompt the user to adjust the shooting angle of the drone to avoid strong direct light sources;

[0165] If N4 is greater than the preset threshold, prompt the user to adjust the shooting angle of the drone to enhance the light source intensity within the field of view of the drone camera;

[0166] If N5 is greater than the preset threshold, decrease the flight speed of the drone by a preset third adjustment base number, increase the flight stability of the drone, and reduce image blur caused by vibration during the flight of the drone.

[0167] The specific process of drone safety supervision is as follows:

[0168] If the first flight safety warning signal is recognized, prompt the user to pay attention to the flight parameters of the drone;

[0169] For the second flight safety warning signal, prompt the user to pay attention that the environment where the drone is located cannot meet the requirements of photogrammetry.

[0170] Please refer to Figure 4 As shown, a drone photogrammetry supervision method includes the following steps:

[0171] Step 1: Data acquisition;

[0172] The drone obtains position and motion data through the Global Navigation Satellite System and the Inertial Measurement Unit, including drone position parameters, velocity vectors, and acceleration vectors. Based on the drone position parameters, velocity vectors, and acceleration, the flight pitch angle and roll angle of the drone are obtained through analysis and calculation.

[0173] Furthermore, image data is obtained through the camera, and the width, height (Hi), pixel brightness, and pixel values of each image are obtained. The environmental parameters include visibility, air pressure, wind speed, and temperature.

[0174] Step 2: Image quality monitoring;

[0175] Check the exposure, contrast, distortion, and sharpness of the images collected by the drone. Based on the brightness values and pixel coordinates of the images, calculate the average exposure, contrast, distortion coefficient, and sharpness gradient value of each image through analysis and operations.

[0176] Furthermore, establish a radial distortion model and a tangential distortion model. Through an image recognition algorithm, locate the landmark reference points and calculate the distortion coefficients to obtain the radial distortion coefficient and the tangential distortion coefficient.

[0177] Step 3: Distortion correction and photogrammetric registration;

[0178] Generate a quality detection feature vector for each image according to the results of exposure, contrast, distortion, and sharpness checks. Based on the image quality feature vector of each image, transfer the image quality detection results and distortion correction results to the photogrammetric registration module through data fusion.

[0179] Perform photogrammetric registration according to the calculation results of the distortion coefficients.

[0180] Extract all images that have not generated overexposure signals, underexposure signals, high-contrast signals, low-contrast signals, and blurry signals, and mark them as feature images.

[0181] Perform distortion correction on all feature images. Inverse-wash the distortion coefficients into the radial distortion model and the tangential distortion model, establish a system of simultaneous equations, and solve for the true values of all pixel coordinates in each image.

[0182] Perform image registration. Extract the coordinates of the known landmark reference points after image distortion correction from each feature image as the feature points of each feature image. Use the known landmark reference points with the same identifier as the anchor points for feature image stitching. Stitch the same known landmark reference points in each feature image to obtain the image registration result.

[0183] Step 4: Environmental safety analysis;

[0184] Calculate and analyze the position parameters and environmental parameters of the drone. Based on the target position deviation, flight speed, and attitude anomaly characteristics of the flight path, obtain the flight safety hazard index through analysis and operations; and obtain the environmental safety hazard index through analysis and operations based on the environmental parameters. If these two indices exceed the set thresholds, trigger flight safety warning and environmental safety warning signals respectively.

[0185] Step 5: Image quality analysis and optimization;

[0186] Statistically count the occurrence times N1, N2, N3, N4, and N5 of overexposure, underexposure, high contrast, low contrast, and blur signals based on the signals output by the image quality detection module. If the occurrence times of a certain signal exceed the preset threshold, corresponding adjustment measures shall be taken according to the type of the detected signal:

[0187] If the overexposure signal N1 exceeds the threshold, adjust the shutter speed and ISO value of the camera;

[0188] If the underexposure signal N2 exceeds the threshold, increase the ISO and adjust the shutter speed;

[0189] If the high contrast signal N3 exceeds the threshold, prompt to adjust the shooting angle;

[0190] If the low contrast signal N4 exceeds the threshold, enhance the light source intensity;

[0191] If the blur signal N5 exceeds the threshold, reduce the flight speed and enhance the stability.

[0192] Step Six: Safety Warning and Execution Feedback;

[0193] Based on the environmental analysis module and the results of image quality supervision, the feedback execution module makes corresponding feedback according to the flight safety warning signal and the environmental safety warning signal. If it is detected that the flight safety hazard exceeds the threshold, remind the user to adjust the flight parameters; if the environmental conditions do not meet the requirements of photogrammetry, prompt the user that the environment cannot meet the requirements and it may be necessary to adjust the flight route or perform environmental compensation.

[0194] It should be understood that the terms "including" and "comprising" used in the specification and claims of this disclosure indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0195] It should also be understood that the terms used in this disclosure specification are only for the purpose of describing specific embodiments and are not intended to limit this disclosure. As used in this disclosure specification and claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms. It should be further understood that the term "and / or" used in this disclosure specification and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations;

[0196] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments only. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A UAV photogrammetry monitoring system, comprising a data acquisition module, an image quality detection module, a photogrammetry registration module and an environment analysis module, characterized in that: The data acquisition module is responsible for collecting the drone’s position parameters, image data, and environmental parameters through the drone’s onboard sensors and cameras; The image quality detection module obtains the UAV image data, performs image quality detection through exposure detection, contrast detection, distortion detection and clarity detection, and performs data fusion on the detection results, analyzes the image quality problems occurring during the photogrammetry process, and generates signals corresponding to the exposure detection, contrast detection, distortion detection and clarity detection results; The photogrammetry registration module obtains the UAV image data and performs distortion correction and photogrammetry registration based on the distortion inspection results of the image quality detection module; The environmental analysis module calculates and analyzes the collected UAV position parameters and environmental parameters, identifies potential flight safety hazards, and outputs signals corresponding to the analysis results of the UAV position parameters and environmental parameters.

2. The unmanned aerial vehicle photogrammetry monitoring system according to claim 1 is characterized in that: Also includes feedback execution module: The feedback execution module monitors the image quality by analyzing the signal output by the image quality detection module of the processing module; and monitors the safety of the drone by analyzing the signal output by the environmental analysis module.

3. The unmanned aerial vehicle photogrammetry monitoring system according to claim 1 is characterized in that: The specific process of collecting drone location parameters, image data and environmental parameters is as follows: The specific process of collecting the location parameters of the drone is as follows: access the global navigation satellite system to obtain the location parameters of the drone, including the latitude, longitude and altitude of the drone; access the inertial measurement unit to obtain the current speed and acceleration of the drone in the east-west, north-south and vertical directions; The pitch angle and roll angle of the UAV flight are obtained by calculating the current acceleration of the UAV in the east-west direction, north-south direction and vertical direction; The specific process of collecting drone image data is as follows: access the images taken by the drone through the camera, obtain the height and width of each image; obtain the pixel coordinates, pixel brightness and pixel value of all pixels in each image; The specific process of collecting UAV environmental parameters is: obtaining the maximum visibility, air pressure, wind speed and temperature of the UAV's location; sending the UAV image data to the image quality detection module; and sending the UAV location parameters and environmental parameters to the environmental analysis module.

4. The unmanned aerial vehicle photogrammetry monitoring system according to claim 1, characterized in that: The specific process of performing exposure check, contrast check, distortion check and clarity check is as follows: The specific process of exposure inspection is as follows: The average exposure of each image is obtained by calculating the pixel coordinates and pixel brightness; The specific process of contrast check is as follows: The contrast of each image is obtained by calculating the pixel coordinates, pixel brightness and the average exposure of each image; The specific process of distortion inspection is as follows: The radial distortion model is established by combining the pixel distance after radial distortion, the pixel distance when no radial distortion occurs ideally, and the radial distortion coefficient: The tangential distortion model is established by combining the pixel coordinates after tangential distortion, the pixel coordinates when no tangential distortion occurs in an ideal state, and the tangential distortion coefficient: Using an image recognition algorithm, each known landmark reference point is located in each image, and the actual world coordinates and pixel coordinates in the image corresponding to each known landmark reference point are obtained; The estimated pixel coordinates of each known landmark reference point in each image are obtained by calculating the actual world coordinates corresponding to each known landmark reference point; The pixel distance after radial distortion is calculated by the pixel coordinates of each known landmark reference point in the image; the pixel distance when no radial distortion occurs under ideal conditions is calculated by the inferred pixel coordinates of each known landmark reference point; the pixel distance after radial distortion and the pixel distance when no radial distortion occurs under ideal conditions are input into the radial distortion model, and an equation with the distortion function as the independent variable is generated for each known landmark reference point in each image; a set of simultaneous equations is established to solve the radial distortion coefficient; The pixel coordinates of each known landmark reference point in the image are input into the tangential distortion model as the pixel coordinates after tangential distortion; the inferred pixel coordinates of each known landmark reference point are input into the tangential distortion model as the pixel coordinates when no tangential distortion occurs under ideal conditions; for each known landmark reference point in each image, an equation with the tangential distortion function as the independent variable is generated, a set of simultaneous equations is established, and the tangential distortion coefficient is solved; The specific process of clarity inspection is as follows: Calculate the horizontal gradient and vertical gradient of each image at all pixel coordinates in the image by operating the pixel values; obtain the average gradient amplitude of each image by operating the horizontal gradient and vertical gradient of each image at all pixel coordinates in the image; The radial distortion coefficient and tangential distortion coefficient of the image taken by the drone are sent to the photogrammetry registration module after the distortion check; the average exposure, contrast and average gradient amplitude of the image taken by the drone are sent to the image quality detection module after the exposure check, contrast check and clarity check.

5. The unmanned aerial vehicle photogrammetry monitoring system according to claim 4, characterized in that: The specific process of analyzing image quality problems that occur during photogrammetry is: The following numerical judgments are made on the average exposure, contrast, and average gradient amplitude produced for the same image: If the average exposure of the image is greater than the maximum threshold, the overall exposure of the image is judged to be too strong, resulting in loss of image details, and an overexposure signal corresponding to the image is output; if the average exposure of the image is less than the minimum threshold, the overall illumination of the image is judged to be too weak, resulting in unrecognizable image areas, and an underexposure signal of the image is output; If the contrast of the image is greater than the maximum threshold, it is determined that the image details are overly exaggerated, resulting in extreme colors, and a high-contrast signal is output; if the contrast of the image is less than the minimum threshold, it is determined that the image lacks details and layers, and effective photogrammetric information cannot be extracted from it, and a low-contrast signal is output; If the average gradient amplitude of the image is lower than the minimum threshold, the image is judged to be overly blurred, and the details therein cannot be distinguished, thus generating a blurred signal; All generated signals are output to the photogrammetry registration module and the feedback execution module.

6. The unmanned aerial vehicle photogrammetry monitoring system according to claim 1, characterized in that: The specific process of distortion correction and photogrammetry registration is as follows: Extract all images that do not generate overexposure signals, underexposure signals, high contrast signals, low contrast signals and blurred signals, and mark them as feature images; Perform distortion correction on all feature images, extract radial distortion coefficients and input them into the radial distortion model; extract tangential distortion coefficients and input them into the tangential distortion model, and establish a set of simultaneous equations to solve the true values ​​of all pixel coordinates in each image; Image registration is performed. The coordinates of each known landmark reference point after image distortion correction are extracted from each feature image as the feature points of each feature image. The known landmark reference points with the same identifier are used as anchor points for feature image stitching. The same known landmark reference points j in each feature image are stitched together to obtain the image registration result.

7. The unmanned aerial vehicle photogrammetry monitoring system according to claim 1, characterized in that: The specific process of comprehensively analyzing the drone's position parameters and identifying potential flight safety hazards is as follows: Obtain the latitude, longitude and altitude of the drone's location and the latitude, longitude and altitude of the target's flight location, and calculate the target position deviation characteristic value through calculation; Obtain the current speed of the drone in the east-west, north-south and vertical directions, and obtain the speed limit characteristic value through calculation; Obtain the pitch angle and roll angle of the drone, and obtain the abnormal attitude feature value through calculation; The flight safety hazard index is obtained by calculating the target position deviation characteristic value, the speed excess characteristic value and the posture abnormality characteristic value; if the flight safety hazard index is greater than the preset threshold, the first flight safety warning signal is output.

8. The unmanned aerial vehicle photogrammetry monitoring system according to claim 1, characterized in that: The specific process of comprehensively analyzing the environmental parameters of drones and identifying potential flight safety hazards is as follows: Get the maximum visibility, air pressure, wind speed and temperature of the drone's location; The visibility exceeding limit characteristic value is obtained by calculating the maximum visibility of the position of the UAV; The air pressure exceeding limit characteristic value is obtained by calculating the air pressure at the position where the UAV is located; The wind speed exceeding limit characteristic value is obtained by calculating the wind speed at the location of the UAV; The temperature exceeding limit characteristic value is obtained by calculating the temperature at the location of the UAV; The environmental safety hazard index is obtained by calculating the UAV's visibility exceeding limit characteristic value, air pressure exceeding limit characteristic value, wind speed exceeding limit characteristic value and temperature exceeding limit characteristic value; If the environmental safety hazard index is greater than the preset threshold, a second flight safety warning signal is output.

9. The unmanned aerial vehicle photogrammetry monitoring system according to claim 2, characterized in that: The specific process of image quality supervision and drone safety supervision is as follows: The specific process of image quality supervision is as follows: Obtain all overexposure signals, underexposure signals, high contrast signals, low contrast signals and blurred signals, and count their occurrence times; If the number of times the overexposure signal is generated is greater than a preset threshold, the shutter speed of the camera is increased by a preset first adjustment base, and the ISO value of the camera is reduced by a preset second adjustment base; If the number of times the underexposure signal is generated is greater than a preset threshold, the shutter speed of the camera is reduced by a preset first adjustment base, and the ISO value of the camera is increased by a preset second adjustment base; If the number of high-contrast signals generated is greater than the preset threshold, the user is prompted to adjust the drone's shooting angle to avoid strong direct light sources; If the number of low-contrast signals generated is greater than a preset threshold, the user is prompted to adjust the drone’s shooting angle to increase the intensity of the light source within the drone’s camera’s field of view; If the number of times the blur signal is generated is greater than a preset threshold, the flight speed of the drone is reduced by a preset third adjustment base, thereby increasing the flight stability of the drone and reducing image blur caused by vibration during the flight of the drone; The specific process of drone safety supervision is as follows: If the first flight safety warning signal is identified, the user is prompted to pay attention to the flight parameters of the drone; The second flight safety warning signal reminds the user that the environment where the drone is located cannot meet the photogrammetry requirements.

10. A method for monitoring unmanned aerial vehicle photogrammetry, characterized in that: The following steps are involved: Step 1: Data collection; The drone obtains position and motion data through the global navigation satellite system and inertial measurement unit, including the drone's position parameters, velocity vector and acceleration vector; based on the drone's position parameters, velocity vector and acceleration, the drone's flight pitch angle and roll angle are obtained through analytical calculation; The image data is acquired through the camera, and the width, height (Hi), pixel brightness and pixel value of each image are obtained; environmental parameters include visibility, air pressure, wind speed and temperature; Step 2: Image quality monitoring; The exposure, contrast, distortion and clarity of the images collected by the drone are checked; according to the brightness value and pixel coordinates of the image, the average exposure, contrast, distortion coefficient and clarity gradient value of each image are obtained through analysis and calculation; Establish radial distortion model and tangential distortion model, locate landmark reference points through image recognition algorithm, calculate distortion coefficient, and obtain radial distortion coefficient and tangential distortion coefficient; Step 3: Distortion correction and photogrammetry registration; Generate a quality detection feature vector for each image based on the exposure, contrast, distortion and clarity inspection results; and pass the image quality inspection results and distortion correction results to the photogrammetry registration module through data fusion based on the image quality feature vector of each image. Perform photogrammetric registration based on the distortion coefficient calculation results; Extract all images that do not generate overexposure signals, underexposure signals, high contrast signals, low contrast signals and blurred signals, and mark them as feature images; Perform distortion correction on all feature images, input the distortion coefficients backwashed into the radial distortion model and the tangential distortion model, establish a set of simultaneous equations, and solve the true values ​​of all pixel coordinates in each image; Perform image registration, extract the coordinates of known landmark reference points after image distortion correction from each feature image as feature points of each feature image, use known landmark reference points with the same identifier as anchor points for feature image stitching, stitch the same known landmark reference points in each feature image to obtain image registration results; Step 4: Environmental safety analysis; Calculate and analyze the position parameters and environmental parameters of the drone; obtain the flight safety hazard index through analysis and calculation based on the target position deviation, flight speed and abnormal attitude characteristics of the flight path; and obtain the environmental safety hazard index through analysis and calculation based on the environmental parameters; if these two indices exceed the set thresholds, the flight safety alarm and environmental safety alarm signals will be triggered respectively; Step 5: Image quality analysis and optimization; According to the signal output by the image quality detection module, the number of times N1, N2, N3, N4 and N5 of overexposure, underexposure, high contrast, low contrast and blur signals are generated is counted; if the number of a certain signal exceeds the preset threshold, the corresponding adjustment measures are taken according to the detection signal type: If the overexposure signal N1 exceeds the threshold, the shutter speed and ISO value of the camera are adjusted; If the underexposure signal N2 exceeds the threshold, the ISO is increased and the shutter speed is adjusted; If the high contrast signal N3 exceeds the threshold, it will prompt to adjust the shooting angle; If the low contrast signal N4 exceeds the threshold, the light source intensity is increased; If the fuzzy signal N5 exceeds the threshold, the flight speed is reduced to enhance stability; Step 6: Security warning and execution feedback; According to the results of the environmental analysis module and image quality supervision, the feedback execution module will provide corresponding feedback based on the flight safety warning signal and the environmental safety warning signal; if it is detected that the flight safety hazard exceeds the threshold, the user will be reminded to adjust the flight parameters; if the environmental conditions do not meet the photogrammetry requirements, the user will be prompted that the environment cannot meet the requirements and the flight route needs to be adjusted or environmental compensation needs to be performed.

Images