Power transmission line point cloud data updating method and system based on dynamic collection of unmanned aerial vehicle

Abstract

The invention provides a power transmission line point cloud data updating method and system based on dynamic collection of an unmanned aerial vehicle, and relates to the technical field of point cloud data processing, and the method comprises the steps: obtaining current point cloud data, flight parameters and environment parameters, dividing the current point cloud data into a plurality of sub-point cloud data, and carrying out the updating of the point cloud data based on the flight parameters and the environment parameters; according to the method, the flight parameter features, the environment parameter features and the quality evaluation features corresponding to the sub-point cloud data are obtained, then the confidence coefficient for comprehensively evaluating the reliability degree of the sub-point cloud data is generated, and finally the original point cloud data are updated in combination with the confidence coefficient and the sub-point cloud data. The accuracy of the updated point cloud data is greatly improved, and the problem that the deviation between the updated point cloud data and the actual situation is too large is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of point cloud data processing, and specifically provides a method and system for updating transmission line point cloud data dynamically collected by an unmanned aerial vehicle. Background Art

[0002] In recent years, with the development of data acquisition technologies such as unmanned aerial vehicles and three-dimensional laser scanning, the acquisition cost and time cycle of three-dimensional laser point cloud data have been effectively reduced. Therefore, three-dimensional laser point cloud technology has been widely applied to the monitoring of transmission lines. For example, a visualization method, device, equipment, and medium for transmission line laser point cloud data (classification number G06F) with the authorized announcement number "CN115100364B" obtains the point cloud data structure corresponding to the to-be-displayed laser point cloud data of the target transmission line. For each point cloud data block in the point cloud data structure, part or all of the point cloud data blocks located outside the viewing range are removed from the point cloud data structure. Then, according to the target point cloud data in the point cloud data structure after removal, a point cloud resource file is loaded, and the target point cloud data is rendered to achieve the visualization display of the laser point cloud data. This technology removes the point cloud data blocks located outside the viewing range, avoids loading and rendering invisible point cloud data, reduces the loading amount and rendering amount of the point cloud data, thereby improving the visualization efficiency of the point cloud data, and can reduce the working burden on the computer graphics card and processor, and further reduce the requirements for computer hardware performance, facilitating the implementation of point cloud visualization.

[0003] However, when applying three-dimensional point cloud technology to transmission line monitoring in the above-mentioned prior art, the technical difficulty of point cloud data update is ignored. Transmission lines are often exposed to harsh external environments. Over time, potential hazard points are likely to occur on transmission lines. Therefore, it is particularly important to update the point cloud data of transmission lines. In current point cloud data updates, the method of directly replacing the original point cloud with newly collected point cloud data is often used, while ignoring the key point of whether the newly collected point cloud data is trustworthy. If the newly collected point cloud data is not trustworthy and blindly uses the newly collected point cloud data to replace the original point cloud, it will lead to a large deviation between the updated point cloud data and the actual situation.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for updating transmission line point cloud data dynamically collected by an unmanned aerial vehicle to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A method for updating point cloud data of a transmission line based on dynamic collection by an unmanned aerial vehicle, and the specific steps include:

[0008] S1. Based on a pre-determined flight route, use an unmanned aerial vehicle to collect the current point cloud data of the transmission line, and obtain the flight parameters and environmental parameters of the unmanned aerial vehicle during the collection process in real time. The flight parameters include flight coordinates, flight altitude, and flight speed, and the environmental parameters include temperature, humidity, wind speed, light intensity, and electromagnetic interference power density;

[0009] S2. Segment the current point cloud data to obtain multiple sub-point cloud data, and extract the features of the flight parameters and environmental parameters during the collection process of the sub-point cloud data to obtain flight parameter features and environmental parameter features. The flight parameter features include the mean values of flight altitude and flight speed, the deviation values of flight coordinates, flight altitude, and flight speed, and the flight speed fluctuation value. The environmental parameter features include the mean values of temperature, humidity, wind speed, light intensity, and electromagnetic interference power density;

[0010] S3. Construct and train a point cloud quality feature extraction model with flight parameter features and environmental parameter features as inputs and quality evaluation features as outputs. Input the flight parameter features and environmental parameter features of the sub-point cloud data into the model to obtain quality evaluation features. The quality evaluation features include the point cloud density, data coverage rate, sampling precision error, and data integrity of the sub-point cloud data;

[0011] S4. Generate a confidence level based on the flight parameter features, environmental parameter features, quality evaluation features, and the collection time interval between the current point cloud data and the original point cloud data. The confidence level is used to comprehensively evaluate the reliability of the sub-point cloud data;

[0012] S5. Update the original point cloud data based on the confidence level and the sub-point cloud data.

[0013] Further, the calculation formulas for the mean values of the flight altitude and flight speed are as follows:

[0014]

[0015] In the formula, H(i) and V(i) respectively represent the flight altitude and flight speed of the unmanned aerial vehicle at the position at the i-th collection moment during the collection process of the sub-point cloud data, respectively represent the mean flight altitude and the mean flight speed of the unmanned aerial vehicle during the collection process of the sub-point cloud data. i is the index of the collection moment of the unmanned aerial vehicle during the collection process of the sub-point cloud data, and i ∈ [1, m], where m is the total number of collection moments of the unmanned aerial vehicle during the collection process of the sub-point cloud data;

[0016] The calculation formula for the deviation value of the flight coordinates is as follows:

[0017]

[0018] In the formula, lon(i) and lat(i) respectively represent the longitude and latitude of the position where the UAV is located at the i-th acquisition moment during the process of collecting sub-point cloud data. The longitude lon(i) and the latitude lat(i) together form the flight coordinates of the UAV, lon b (i), lat b (i) respectively represent the longitude and latitude of the position where the UAV should be located according to the established flight route at the i-th acquisition moment during the process of collecting sub-point cloud data. Δlon(i) and Δlat(i) respectively represent the longitude difference and latitude difference between the position where the UAV is located and the position where it should be located at the i-th acquisition moment during the process of collecting sub-point cloud data;

[0019] In the formula, dlon(i) and dlat(i) respectively represent the longitude deviation distance and latitude deviation distance between the position where the UAV is located and the position where it should be located at the i-th acquisition moment during the process of collecting sub-point cloud data. Cpc represents the flight coordinate deviation value of the UAV during the process of collecting sub-point cloud data;

[0020] The calculation formula for the flight height deviation value is as follows:

[0021]

[0022] In the formula, H(i) and H b (i) respectively represent the flight height of the position where the UAV is located and the flight height of the position where it should be located according to the established flight route at the i-th acquisition moment during the process of collecting sub-point cloud data. Hpc represents the flight height deviation value of the UAV during the process of collecting sub-point cloud data;

[0023] The calculation formula for the flight speed deviation value is as follows:

[0024]

[0025] In the formula, V(i) and V b (i) respectively represent the flight speed of the position where the UAV is located and the flight speed of the position where it should be located according to the established flight route at the i-th acquisition moment during the process of collecting sub-point cloud data. Vpc represents the flight speed deviation value of the UAV during the process of collecting sub-point cloud data;

[0026] The calculation formula for the flight speed fluctuation value is as follows:

[0027]

[0028] In the formula, Vbd represents the flight speed fluctuation value of the UAV during the process of collecting sub-point cloud data;

[0029] The mean calculation formulas for the temperature, humidity, wind speed, light intensity, and electromagnetic interference power density are as follows:

[0030]

[0031] In the formula, T(i), RH(i), V f (i), I(i), and E(i) respectively represent the temperature, humidity, wind speed, light intensity, and electromagnetic interference power density of the environment where the UAV is located at the i-th acquisition moment during the process of collecting sub-point cloud data. They respectively represent the mean temperature, mean humidity, mean wind speed, mean light intensity, and mean electromagnetic interference power density of the environment where the UAV is located during the process of collecting sub-point cloud data.

[0032] Furthermore, the process of obtaining the quality evaluation features of the sub-point cloud data is as follows:

[0033] 1.1) Obtain multiple sample point cloud data with known quality evaluation features, flight parameter features, and environmental parameter features, and construct parameter feature vectors for each sample point cloud data based on the flight parameter features and environmental parameter features;

[0034] The method for obtaining the quality evaluation features of the sample point cloud data is as follows:

[0035]

[0036] In the formula, D represents the point cloud density, N represents the number of data points in the point cloud data, A represents the area covered by the point cloud data, O represents the data coverage rate, Ltotal is the planned coverage length for point cloud data collection, Loverlap is the length of the overlapping part in the point cloud data, Δxk, Δyk, and Δzk are the distances in the horizontal direction, vertical direction, and depth direction respectively between the k-th reference point and the sampling point corresponding to the reference point in the point cloud data, k is the index of the reference point, and k ∈ [1, K], where K is the number of reference points, CYwc is the sampling precision error, Nth is the expected number of data points to be collected corresponding to the point cloud data, and WZpg is the data integrity of the point cloud data;

[0037] 1.2) Based on a deep neural network, construct a point cloud quality feature extraction model with the parameter feature vector as the input and the quality evaluation feature as the output. Use the parameter feature vector of the sample point cloud data as the input and the corresponding quality evaluation feature as the output label to train the point cloud quality feature extraction model;

[0038] 1.3) Concatenate the flight parameter features and environmental parameter features of the sub-point cloud data to form a parameter feature vector, and then input the parameter feature vector into the trained point cloud quality feature extraction model to obtain the quality evaluation feature of the sub-point cloud data.

[0039] Further, the calculation process of the confidence level includes the following steps:

[0040] 2.1) Based on the flight parameter features, generate a flight state evaluation coefficient for evaluating the quality of the flight state of the drone when collecting sub-point cloud data. The calculation formula is as follows:

[0041]

[0042] In the formula, FXpg is the flight state evaluation coefficient, is the preset flight speed deviation threshold, is the preset flight coordinate deviation threshold, ω1, ω2, ω3 are the weights of the flight altitude factor, flight speed factor, and flight coordinate factor in the calculation of the flight state evaluation coefficient respectively, and ω1 + ω2 + ω3 = 1, and ω2 > ω1 = ω3;

[0043] 2.2) Based on the environmental parameter features, generate an environmental parameter evaluation coefficient for evaluating the quality of the environmental parameters of the drone when collecting sub-point cloud data. The calculation formula is as follows:

[0044]

[0045] In the formula, HJpg is the environmental parameter evaluation coefficient, T*, RH*, Vf*, I*, E* are the suitable working temperature, suitable working humidity, standard wind resistance value, suitable light intensity, and standard anti-electromagnetic interference ability value of the drone when collecting point cloud data respectively, λ1, λ2, λ3, λ4, λ5 are the weights of the temperature factor, humidity factor, wind speed factor, light intensity factor, and electromagnetic interference factor in the calculation of the environmental parameter evaluation coefficient respectively, and the specific values of λ1, λ2, λ3, λ4, λ5 are determined by the analytic hierarchy process;

[0046] 2.3) Based on the quality evaluation feature, generate a point cloud quality evaluation coefficient for evaluating the quality of the sub-point cloud data collected by the drone. The calculation formula is as follows:

[0047]

[0048] Wherein, DYpg is the point cloud quality evaluation coefficient, D* and O* are respectively the preset appropriate values of point cloud density and data coverage rate, γ1, γ2, γ3, and γ4 are respectively the weights of point cloud density, data coverage rate, sampling precision error, and data integrity in the calculation of the point cloud quality evaluation coefficient, and the specific values of γ1, γ2, γ3, and γ4 are also determined by the analytic hierarchy process;

[0049] 2.4) Generate the confidence level based on the flight state evaluation coefficient, environmental parameter evaluation coefficient, quality evaluation coefficient, and the acquisition time interval between the current point cloud data and the original point cloud data. The calculation formula is as follows:

[0050]

[0051] Wherein, ZXD is the confidence level of the sub-point cloud data, χ1, χ2, and χ3 are respectively the weights of the flight state evaluation coefficient, environmental parameter evaluation coefficient, and quality evaluation coefficient in the confidence level evaluation calculation, and χ1 + χ2 + χ3 = 1, and χ3 > χ1 = χ2, t is the acquisition time interval between the current point cloud data and the original point cloud data, and t0 is the preset update time interval threshold.

[0052] Furthermore, the method for updating the original point cloud data is as follows:

[0053] 3.1) Obtain multiple test transmission line areas, and successively collect point cloud data for the test transmission line areas by using an unmanned aerial vehicle. Take the point cloud data obtained previously as the test original point cloud data, and take the point cloud data obtained later as the test current point cloud data. When collecting the test current point cloud data, collect the test actual point cloud data of the test transmission line area based on ground facilities, and register the test original point cloud data, test current point cloud data, and test actual point cloud data based on the iterative closest point algorithm, and calculate the confidence level of the test current point cloud data based on the same method;

[0054] 3.2) Construct a point cloud update model based on a convolutional neural network, use the registered test original point cloud data, test current point cloud data, and their corresponding confidence levels as inputs, and use the registered test actual point cloud data as the output to train the point cloud update model;

[0055] 3.3) Extract the corresponding sub-point cloud data to be updated from the original point cloud data based on the sub-point cloud data, register the sub-point cloud data and the sub-point cloud data to be updated, and input the registered sub-point cloud data to be updated, sub-point cloud data, and their corresponding confidence levels into the point cloud update model to obtain the updated sub-point cloud data, and input the updated sub-point cloud data into the original point cloud data to replace the sub-point cloud data to be updated.

[0056] A power transmission line point cloud data updating system based on dynamic collection by an unmanned aerial vehicle, for the power transmission line point cloud data updating method based on dynamic collection by an unmanned aerial vehicle as described above, includes:

[0057] A data acquisition module, based on a pre-determined flight route, uses an unmanned aerial vehicle to acquire the current point cloud data of the power transmission line, and in real time obtains the flight parameters and environmental parameters of the unmanned aerial vehicle during the acquisition process. The flight parameters include flight coordinates, flight altitude, and flight speed, and the environmental parameters include temperature, humidity, wind speed, light intensity, and electromagnetic interference power density;

[0058] A feature extraction module, used to segment the current point cloud data to obtain multiple sub-point cloud data, and extract features from the flight parameters and environmental parameters during the acquisition process of the sub-point cloud data to obtain flight parameter features and environmental parameter features. The flight parameter features include the mean values of flight altitude and flight speed, the deviation values of flight coordinates, flight altitude, and flight speed, and the flight speed fluctuation value. The environmental parameter features include the mean values of temperature, humidity, wind speed, light intensity, and electromagnetic interference power density;

[0059] A feature prediction module, used to construct and train a point cloud quality feature extraction model with flight parameter features and environmental parameter features as inputs and quality assessment features as outputs, and input the flight parameter features and environmental parameter features of the sub-point cloud data into the model to obtain quality assessment features. The quality assessment features include the point cloud density, data coverage rate, sampling precision error, and data integrity of the sub-point cloud data;

[0060] A confidence calculation module, based on the flight parameter features, environmental parameter features, quality assessment features, and the acquisition time interval between the current point cloud data and the original point cloud data, generates a confidence level, which is used to comprehensively evaluate the reliability of the sub-point cloud data;

[0061] A point cloud update module, based on the confidence level and the sub-point cloud data, updates the original point cloud data.

[0062] Compared with the prior art, the beneficial effects of the present invention are:

[0063] For the power transmission line point cloud data updating method and system based on dynamic collection by an unmanned aerial vehicle of the present invention, after acquiring the current point cloud data, the current point cloud data is first divided into multiple sub-point cloud data, and then the quality of the sub-point cloud data, the flight state and the environment where the unmanned aerial vehicle acquires the point cloud data are comprehensively evaluated to obtain a confidence level reflecting the reliability of the sub-point cloud data. Finally, based on the confidence level and the sub-point cloud data, the original point cloud data is updated. Compared with the method of direct replacement, the accuracy of the updated point cloud data is greatly improved, and the problem that the updated point cloud data deviates too much from the actual situation is avoided. Description of the Drawings

[0064] Figure 1 This is a schematic diagram of the overall method flow of the present invention;

[0065] Figure 2 This is a schematic diagram of the overall system module of the present invention. Detailed implementation manners

[0066] To make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with specific embodiments.

[0067] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar terms used in the present invention do not represent any order, quantity or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0068] Embodiment:

[0069] Please refer to Figure 1 , the present invention provides a method for updating point cloud data of a transmission line based on dynamic collection by an unmanned aerial vehicle, and the specific steps include:

[0070] S1, based on a pre-determined flight route, use an unmanned aerial vehicle to collect the current point cloud data of the transmission line, and obtain the flight parameters and environmental parameters of the unmanned aerial vehicle during the collection process in real time. The flight parameters include flight coordinates, flight altitude and flight speed, and the environmental parameters include temperature, humidity, wind speed, light intensity and electromagnetic interference power density;

[0071] It should be noted that the specific method for planning the flight route is: according to the layout of the transmission line to be measured, use unmanned aerial vehicle route planning software (such as Mission Planner, Pix4D, etc.) to design the flight route, and ensure that the designed flight route covers all areas of all transmission lines. This is prior art and will not be elaborated here;

[0072] Among them, the unmanned aerial vehicle collects the current point cloud data of the transmission line through the lidar (LiDAR) carried by itself, and the flight coordinates, flight altitude and flight speed can be jointly obtained through the GPS module and inertial measurement unit IMU built in the unmanned aerial vehicle;

[0073] Among them, the environmental parameters are the environmental parameters of the environment where the drone is flying during the flight. The temperature and humidity are specifically obtained through digital temperature and humidity sensors (such as DHT22, SHT31, etc.) installed on the drone. The wind speed can be obtained through plug-in anemometers (such as thermal anemometers, ultrasonic anemometers, etc.) installed on the drone. The light intensity can be obtained through light sensors (such as BH1750, TSL2561, etc.) installed on the drone. The electromagnetic interference power density can be obtained through an electromagnetic field detector installed on the drone. The units of temperature, humidity, wind speed, light intensity, and electromagnetic interference power density are degrees Celsius, %, meters per second, lux, and milliwatts per square meter respectively;

[0074] It should be noted that the electromagnetic interference power density is generally obtained indirectly through an electromagnetic field detector, specifically including: first, measuring the magnetic field strength of the environment where the drone is located according to the electromagnetic field detector, and then multiplying the square of the magnetic field strength by the characteristic impedance of free space to obtain the electromagnetic interference power density. The characteristic impedance of free space generally takes a value of 377 ohms. This is the prior art and will not be elaborated here;

[0075] Among them, in step S1, the flight parameters and environmental parameters are collected at the same acquisition frequency to facilitate subsequent data analysis. The interval between adjacent acquisition times can be 3 seconds, 5 seconds, 10 seconds, etc., which is not limited here. Of course, after collecting the flight parameters and environmental parameters at different acquisition frequencies, the method of unifying the timestamps through data processing methods such as interpolation can also be used, and it is specifically set by the staff according to the actual situation, which is not limited here.

[0076] S2, segment the current point cloud data to obtain multiple sub-point cloud data, and extract the features of the flight parameters and environmental parameters during the acquisition process of the sub-point cloud data to obtain flight parameter features and environmental parameter features. The flight parameter features include the mean values of flight altitude and flight speed, flight coordinates, deviation values of flight altitude and flight speed, and flight speed fluctuation values. The environmental parameter features include the mean values of temperature, humidity, wind speed, light intensity, and electromagnetic interference power density;

[0077] It should be noted that the segmentation can be performed according to the acquisition time, or the current point cloud data can be segmented according to the acquisition length. It is specifically selected by the staff according to the actual situation and is not limited here. The method of segmenting settings facilitates subsequent point cloud data update operations. Compared with the method of updating the point cloud data as a whole, segmenting the point cloud data first and then updating each sub-point cloud data with the corresponding original point cloud data reduces the workload of a single update and can achieve the effect of quickly updating the point cloud data;

[0078] Among them, the method of segmenting according to the acquisition time is as follows: Preset a reasonable time interval (such as every 5 minutes, every 10 minutes, etc.). After completing the acquisition of point cloud data, traverse all the point cloud data, record the timestamp of each data point, determine the minimum timestamp as the first timestamp, use the timestamp that is one time interval away from the minimum timestamp as the second timestamp, use the timestamp that is two time intervals away from the minimum timestamp as the third timestamp, and so on. Intercept the data points whose timestamps are between the first timestamp and the second timestamp to form the first sub-point cloud data, intercept the data points whose timestamps are between the second timestamp and the third timestamp to form the second sub-point cloud data, and so on to complete the segmentation;

[0079] Among them, the method of segmenting according to the acquisition length is as follows: Preset a reasonable length interval (such as every 100 meters, every 200 meters, etc.). After completing the acquisition of point cloud data, select one end as the starting point and the other end as the ending point. With the extension direction from the starting point to the ending point, take the point that is one length interval away from the starting point along the extension direction as the first segmentation point, take the point that is one length interval away from the first segmentation point along the extension direction as the second segmentation point, and so on. Intercept the data points located between the starting point and the first segmentation point to form the first sub-point cloud data, intercept the data points located between the first segmentation point and the second segmentation point to form the second sub-point cloud data, and so on to complete the segmentation;

[0080] Among them, the mean calculation formulas for the flight altitude and flight speed are as follows:

[0081]

[0082] In the formula, H(i) and V(i) respectively represent the flight altitude and flight speed of the UAV at the position at the i-th acquisition moment during the acquisition of the sub-point cloud data, respectively represent the mean flight altitude and the mean flight speed of the UAV during the acquisition of the sub-point cloud data. i is the index of the acquisition moment of the UAV during the acquisition of the sub-point cloud data, and i ∈ [1, m], where m is the total number of acquisition moments of the UAV during the acquisition of the sub-point cloud data;

[0083] Among them, the calculation formula for the flight coordinate deviation value is as follows:

[0084]

[0085] In the formula, lon(i) and lat(i) respectively represent the longitude and latitude of the UAV at the position at the i-th acquisition moment during the acquisition of the sub-point cloud data. The longitude lon(i) and the latitude lat(i) together form the flight coordinates of the UAV, lon b (i), lat b(i) respectively represent the longitude and latitude of the UAV's supposed position at the i-th acquisition moment during the process of collecting sub-point cloud data. Δlon(i) and Δlat(i) respectively represent the longitude difference and latitude difference between the UAV's actual position and the supposed position at the i-th acquisition moment during the process of collecting sub-point cloud data;

[0086] In the formula, dlon(i) and dlat(i) respectively represent the longitude deviation distance and latitude deviation distance (in meters) between the UAV's actual position and the supposed position at the i-th acquisition moment during the process of collecting sub-point cloud data. The formulas for converting longitude difference and latitude difference into longitude deviation distance and latitude deviation distance are prior arts and will not be explained here;

[0087] In the formula, Cpc represents the flight coordinate deviation value of the UAV during the process of collecting sub-point cloud data, which is used to characterize the severity of the UAV's flight coordinates deviating from the established flight route during the process of collecting sub-point cloud data. The larger the longitude deviation distance and latitude deviation distance, the higher the degree of the UAV deviating from the established flight route during the process of collecting sub-point cloud data, the larger the flight coordinate deviation value, and the worse the credibility of the sub-point cloud data collected by the UAV;

[0088] Among them, the calculation formula for the flight altitude deviation value is as follows:

[0089]

[0090] In the formula, H(i) and H b (i) respectively represent the flight altitude of the UAV's actual position and the supposed position at the i-th acquisition moment during the process of collecting sub-point cloud data. Hpc represents the flight altitude deviation value of the UAV during the process of collecting sub-point cloud data, which is used to characterize the severity of the UAV's flight altitude deviating from the established flight route during the process of collecting sub-point cloud data. The larger the absolute difference between H(i) and H b (i), the higher the degree of the UAV deviating from the established flight route during the process of collecting sub-point cloud data, the larger the flight altitude deviation value, and the worse the credibility of the sub-point cloud data collected by the UAV;

[0091] Among them, the calculation formula for the flight speed deviation value is as follows:

[0092]

[0093] In the formula, V(i) and V b(i) respectively represent the flight speed of the UAV at the i-th acquisition moment during the process of collecting sub-point cloud data and the flight speed at the position that should be according to the established flight route. Vpc represents the flight speed deviation value of the UAV during the process of collecting sub-point cloud data, which is used to characterize the severity of the flight speed of the UAV deviating from the established flight route during the process of collecting sub-point cloud data. The greater the absolute difference between V(i) and V b (i), the higher the degree of deviation of the UAV from the established flight route during the process of collecting sub-point cloud data, the greater the flight speed deviation value, and the worse the credibility of the sub-point cloud data collected by the UAV;

[0094] Among them, the calculation formula of the flight speed fluctuation value is as follows:

[0095]

[0096] In the formula, Vbd represents the flight speed fluctuation value of the UAV during the process of collecting sub-point cloud data, which is used to characterize the fluctuation of the flight speed of the UAV during the process of collecting sub-point cloud data. The greater the flight speed fluctuation value, the more unstable the flight speed of the UAV during the process of collecting sub-point cloud data, the greater the adverse impact on the process of the UAV collecting sub-point cloud data, and the worse the credibility of the sub-point cloud data collected by the UAV;

[0097] Among them, the calculation formula of the mean values of temperature, humidity, wind speed, light intensity and electromagnetic interference power density is as follows:

[0098]

[0099] In the formula, T(i), RH(i), V f (i), I(i), E(i) respectively represent the temperature, humidity, wind speed, light intensity and electromagnetic interference power density of the environment where the UAV is located at the i-th acquisition moment during the process of collecting sub-point cloud data, respectively represent the mean value of temperature, mean value of humidity, mean value of wind speed, mean value of light intensity and mean value of electromagnetic interference power density of the environment where the UAV is located during the process of collecting sub-point cloud data.

[0100] S3. Construct and train a point cloud quality feature extraction model with flight parameter features and environmental parameter features as inputs and quality evaluation features as outputs. Input the flight parameter features and environmental parameter features of the sub-point cloud data into the model to obtain quality evaluation features, and the quality evaluation features include the point cloud density, data coverage rate, sampling precision error and data integrity of the sub-point cloud data;

[0101] Among them, the process of constructing and training the point cloud quality feature extraction model is as follows:

[0102] 1.1) Obtain the sample point cloud data of multiple known quality evaluation features, flight parameter features, and environmental parameter features. Based on the flight parameter features and environmental parameter features, construct the parameter feature vectors of each sample point cloud data. The representation of the parameter feature vector is as follows:

[0103]

[0104] In the formula, CSxl represents the parameter feature vector, which represents the state of the point cloud data collected by the UAV from two dimensions of flight parameters and environmental parameters, so as to facilitate subsequent prediction and analysis of the quality evaluation features of the sample point cloud data through these parameter features;

[0105] It should be noted that the sample point cloud data is the point cloud data of other transmission lines. Due to the similarity of the same transmission line, the constructed point cloud quality feature extraction model is more targeted, thereby improving the accuracy of the subsequent point cloud quality feature extraction model in predicting the quality evaluation features of the sub-point cloud data. The acquisition methods of the flight parameter features and environmental parameter features corresponding to the sample point cloud data are the same as those above and will not be elaborated here. The quality evaluation feature acquisition method is as follows:

[0106]

[0107] In the formula, D represents the point cloud density, N represents the number of data points in the point cloud data, which can be directly recorded by the sensor during the point cloud data acquisition process, A represents the area covered by the point cloud data, which can be obtained through point cloud data processing software such as pix4D and QGIS. The greater the point cloud density, the more data points per unit area;

[0108] In the formula, O represents the data coverage rate, Ltotal is the planned coverage length (i.e., the total route length) during the point cloud data acquisition, Loverlap is the length of the overlapping part in the point cloud data, which can be obtained through point cloud data processing software such as Pix4D and Agisoft Metashap. The greater the data coverage rate, the more duplicate data points in the point cloud data;

[0109] In the formula, Δxk, Δyk, and Δzk are the distances in the horizontal direction, vertical direction, and depth direction respectively between the k-th reference point and the sampling point corresponding to this reference point in the point cloud data. k is the index of the reference point, and k ∈ [1, K], where K is the number of reference points. The selection method for Δxk, Δyk, and Δzk is as follows: In the real area corresponding to the point cloud data, randomly determine K reference points, and use high-precision ground measurement data to obtain their position coordinates. Then, based on point cloud data processing software such as Pix4D and Agisoft Metashap, determine the position coordinate information of the reference point in the point cloud data. Convert the two obtained position coordinates into the real three-dimensional coordinate system to obtain Δxk, Δyk, and Δzk. is set to convert the absolute error into a relative error compared to the coverage length of the entire point cloud data, so as to more intuitively reflect the sampling accuracy error. CYwc is the sampling accuracy error;

[0110] In the formula, Nth is the expected number of data points to be collected corresponding to the point cloud data. It can be determined by planning before the point cloud data is collected, or the product of the average collection frequency and the collection time during the point cloud data collection by the unmanned aerial vehicle can be used as the expected number of data points to be collected. WZpg is the data integrity of the point cloud data. The larger its value, the more in line with expectations the collection of the point cloud data is, and the more complete the collected point cloud data is;

[0111] 1.2) Construct a point cloud quality feature extraction model with the input being the parameter feature vector and the output being the quality assessment feature. Use the parameter feature vector of the sample point cloud data as the input and the corresponding quality assessment feature as the output label to train the point cloud quality feature extraction model. The specific training process is as follows:

[0112] Mark each quality assessment feature on the corresponding parameter feature vector one by one. Combine the parameter feature vectors after marking to form a data set, and randomly divide the data set into a training set and a test set according to the ratio of 80 to 20. Use the training set to train the point cloud quality feature extraction model, and use the mean square error as the loss function during the training process. Iteratively optimize the model parameters by minimizing the difference between the model prediction value and the actual value, and use cross-validation to select the optimal model hyperparameters to avoid overfitting. After reaching the predetermined number of iterations, use the test set to test the processing time prediction model. If it meets the test requirements, it is considered that the training is completed; otherwise, retrain until the test requirements are met. The specific test requirements can be set as the accuracy of the model prediction value not being lower than 90%, 92%, 95%, etc., which is not restricted here;

[0113] 1.3) Concatenate the flight parameter features and environmental parameter features of the sub-point cloud data to form a parameter feature vector, and then input the parameter feature vector into the trained point cloud quality feature extraction model to obtain the quality evaluation features of the sub-point cloud data;

[0114] It should be noted that to improve the convergence speed and performance of the point cloud quality feature extraction model, the data belonging to the same category in the data set and the sub-point cloud data (such as the point cloud density of the sub-point cloud data and the point cloud density of the sample point cloud data in the data set belonging to the same category of data) can be subjected to maximum-minimum normalization processing together to unify the dimensions of various types of data, thereby improving the convergence speed and performance of the subsequent point cloud quality feature extraction model.

[0115] S4. Generate a confidence level based on the flight parameter features, environmental parameter features, quality evaluation features, and the acquisition time interval between the current point cloud data and the original point cloud data. The confidence level is used to comprehensively evaluate the reliability of the sub-point cloud data, including the following steps:

[0116] 2.1) Based on the flight parameter features, generate a flight state evaluation coefficient for evaluating the quality of the flight state of the UAV when collecting the sub-point cloud data. The calculation formula is as follows:

[0117]

[0118] In the formula, FXpg is the flight state evaluation coefficient, which comprehensively evaluates the flight state of the UAV when collecting the sub-point cloud data from three aspects: the flight height factor, the flight coordinate factor, and the flight speed factor, by combining the mean values of the flight height and flight speed, the flight coordinates, the deviation values of the flight height and flight speed, and the flight speed fluctuation value. And the larger the flight state evaluation index, the worse the flight state of the UAV when collecting the sub-point cloud data, indicating that the credibility of the sub-point cloud data collected by the UAV is lower;

[0119] It should be noted that the larger the flight height deviation value, the greater the deviation between the flight height of the UAV when collecting the sub-point cloud data and the flight height planned by the established flight route, indicating that the degree of deviation of the UAV from the flight route during flight is greater. And the setting of the ratio is used to evaluate the relative deviation degree of the flight height with the mean flight height as the evaluation benchmark. The larger the ratio , the greater the relative deviation degree of the flight height of the UAV when collecting the sub-point cloud data, and the worse the credibility of the collected sub-point cloud data. Therefore, the ratio is used as a component of calculating the flight state evaluation coefficient;

[0120] It should be noted that if the flight speed of the UAV is too low when collecting sub-point cloud data, a large amount of unnecessary duplicate data points will be generated, increasing the difficulty of subsequent data processing. On the other hand, if the flight speed is too fast, the number of collected data points will be too small, which is not conducive to analyzing the condition of the transmission line based on the point cloud data subsequently. Whether the flight speed is too high or too low will cause the flight speed deviation value to increase, thereby reducing the credibility of the sub-point cloud data collected by the UAV. Moreover, as the flight speed deviation value increases, the credibility of the sub-point cloud data drops rapidly. Therefore, the flight speed deviation value is regarded as an important influencing factor for evaluating the flight state of the UAV. In the formula, is the preset flight speed deviation threshold, and its value is set by the staff according to the actual situation. For example, it can be set to 10% to 20% of the average flight speed of the established flight route. When the flight speed deviation value exceeds the flight speed deviation threshold, it indicates that the current flight speed is extremely unreasonable. If the flight speed deviation value continues to increase, the credibility of the sub-point cloud data collected by the UAV drops rapidly. Therefore, the form of is used to characterize the non-linear influence of the flight speed deviation value on the flight state. As the flight speed deviation value increases, the unbelievability of the sub-point cloud data collected by the UAV gradually increases. And when the flight speed deviation value exceeds the flight speed deviation threshold, as the flight speed deviation value continues to increase, increases rapidly, thereby reflecting the phenomenon that the credibility of the sub-point cloud data drops rapidly due to excessive flight speed deviation;

[0121] Furthermore, when analyzing the flight speed factor to evaluate the flight state of the UAV, the stability of the flight speed is also one of the important considerations. A stable flight speed can help the UAV collect sub-point cloud data of high quality. On the contrary, an unstable flight speed will lead to a problem of reduced credibility of the collected sub-point cloud data. The ratio is used to reflect the relative volatility of the UAV when collecting sub-point cloud data. The larger the ratio , the worse the stability of the UAV when collecting sub-point cloud data, and the worse the credibility of the collected sub-point cloud data. Therefore, is introduced to correct , so as to comprehensively evaluate the flight speed factor when evaluating the flight state of the UAV;

[0122] It should be noted that the larger the flight coordinate deviation value, the greater the deviation between the flight coordinates of the UAV and the flight coordinates planned by the established flight route when collecting sub-point cloud data, which means that the degree of deviation of the UAV from the flight route during flight is greater, and the credibility of the collected sub-point cloud data is worse. In the formula, is a preset flight coordinate deviation threshold, and its value is set by the staff according to the actual situation. For example, it can be set to a fixed value of 1 meter, or it can be set to be between one-thousandth and one-hundredth of the length of the area where the sub-point cloud data is located. Its role is to provide a reference for the flight coordinate deviation value, so as to facilitate the staff to quantify the deviation degree represented by the flight coordinate deviation value. The ratio is set to use the flight coordinate deviation threshold as the evaluation benchmark to evaluate the relative deviation degree of the flight coordinates. The ratio The larger it is, the greater the relative deviation degree of the flight coordinates when the UAV is collecting sub-point cloud data. Therefore, the ratio is used as a component of calculating the flight state evaluation coefficient;

[0123] In the formula, ω1, ω2, and ω3 are the weights of the flight height factor, flight speed factor, and flight coordinate factor in the calculation of the flight state evaluation coefficient respectively. When the UAV collects sub-point cloud data, the acquisition quality of the sub-point cloud data depends to a large extent on the flight speed, that is, the flight speed factor is the most sensitive influencing factor, and the flight speed also determines the flight height deviation and flight coordinate deviation to a large extent. Therefore, the flight speed factor is given the largest weight, and both the flight height deviation and flight coordinate deviation reflect the distance of the UAV deviating from the established flight path. Therefore, the flight height and flight coordinates are given the same weight. Based on ω1 + ω2 + ω3 = 1, let ω2 > ω1 = ω3, and the specific values of the three are debugged and used by the staff according to the actual situation on this basis, and no more restrictions are imposed here;

[0124] 2.2) Based on the characteristics of environmental parameters, generate an environmental parameter evaluation coefficient for evaluating the quality of environmental parameters when the UAV collects sub-point cloud data. The calculation formula is as follows:

[0125]

[0126] In the formula, HJpg is the environmental parameter evaluation coefficient, which comprehensively evaluates the environment where the UAV collects sub-point cloud data from five aspects: temperature, humidity, wind speed, light intensity, and electromagnetic interference power density. The larger the environmental parameter evaluation coefficient, the worse the environment where the UAV collects sub-point cloud data, that is, the lower the credibility of the sub-point cloud data collected by the UAV;

[0127] In the formula, T*, RH*, Vf*, I*, and E* are the suitable working temperature, suitable working humidity, standard wind resistance value, suitable light intensity, and standard anti-electromagnetic interference ability value when the UAV collects point cloud data respectively;

[0128] It should be noted that the suitable working temperature, suitable working humidity, and suitable light intensity are all environmental parameters suitable for the UAV to collect point cloud data. The UAV can collect point cloud data most accurately in this environment. Among them, the value of the suitable working temperature ranges from 20 to 25 degrees Celsius, the value of the suitable working humidity ranges from 30% to 50%, and the value range of the suitable light intensity q is between 4000 and 7000 lux. The specific values are set by the staff according to the actual situation;

[0129] It should be noted that the standard wind resistance value means that when the wind speed is below this value, the UAV can still maintain good stability to ensure good collection accuracy. When the wind speed exceeds this value, the stability of the UAV will be greatly reduced due to the increase in wind speed, resulting in a rapid decline in the credibility of the collected data. The specific value of the standard wind resistance value is determined according to the type of UAV. For example, for small consumer UAVs, the standard wind resistance value is 5 meters per second, which means that when the wind speed is below 5 meters per second, the small consumer UAV can still maintain good stability to ensure good collection accuracy. When the wind speed exceeds 5 meters per second, the stability of the small consumer UAV will be greatly reduced due to the increase in wind speed, resulting in a rapid decline in the credibility of the collected data. Similarly, for medium-sized commercial UAVs, the standard wind resistance value is 9 meters per second, and for large industrial UAVs, the standard wind resistance value is 12 meters per second. The standard anti-electromagnetic interference ability value means that when the electromagnetic interference power density is below this value, the UAV can still maintain good anti-interference ability to ensure good collection accuracy. When the electromagnetic interference power density exceeds this value, the stability of the UAV will be greatly reduced due to the increase in wind speed, resulting in a rapid decline in the credibility of the collected data. The standard anti-electromagnetic interference ability value can range from 0.5 to 1.5 milliwatts per square meter;

[0130] It should be noted that is used to characterize the deviation degree of the temperature mean value from the suitable working temperature. The larger its value, the worse the temperature factor, the more unfavorable it is for the UAV to collect sub-point cloud data, and the worse the credibility of the collected sub-point cloud data. Similarly is used to characterize the deviation degree of the humidity mean value from the suitable working humidity. The larger its value, the worse the humidity factor, the more unfavorable it is for the UAV to collect sub-point cloud data, and the worse the credibility of the collected sub-point cloud data, is used to characterize the deviation degree of the light intensity mean value from the suitable light intensity. The larger its value, the worse the light intensity factor, the more unfavorable it is for the UAV to collect sub-point cloud data, and the worse the credibility of the collected sub-point cloud data;

[0131] It should be noted that It is used to characterize the quality of the wind speed in the environment when the drone collects sub-point cloud data. The larger the mean wind speed, the worse the wind speed in the environment when the drone collects sub-point cloud data, and the less reliable the collected sub-point cloud data. is formed to characterize the non-linear influence of wind speed on the collection accuracy of the drone. It shows that as the wind speed increases, the adverse effect of wind speed on the collection accuracy of the drone increases slowly at first. Until the mean wind speed is greater than the standard wind resistance value, as the mean wind speed increases, the collection accuracy of the drone drops rapidly, and then the credibility of the collected sub-point cloud data drops rapidly. Similarly It is used to characterize the quality of the electromagnetic interference power density in the environment when the drone collects sub-point cloud data. The larger the mean electromagnetic interference power density, the worse the electromagnetic interference power density in the environment when the drone collects sub-point cloud data, and the less reliable the collected sub-point cloud data. is formed to characterize the non-linear influence of electromagnetic interference power density on the collection accuracy of the drone. It shows that as the electromagnetic interference power density increases, the adverse effect of electromagnetic interference on the collection accuracy of the drone increases slowly at first. Until the mean electromagnetic interference power density is greater than the standard anti-electromagnetic interference ability value, as the mean electromagnetic interference power density increases, the collection accuracy of the drone drops rapidly, and then the credibility of the collected sub-point cloud data drops rapidly;

[0132] In the formula, λ1, λ2, λ3, λ4, and λ5 are the weights of the temperature factor, humidity factor, wind speed factor, light intensity factor, and electromagnetic interference factor in the calculation of the environmental parameter evaluation coefficient, respectively. The specific values of λ1, λ2, λ3, λ4, and λ5 are determined by the analytic hierarchy process. The specific logic is as follows:

[0133] Mark the five factors of temperature factor, humidity factor, wind speed factor, light intensity factor, and electromagnetic interference factor, and determine the numerical values of the relative importance between each other through the nine-scale method to construct a judgment matrix. Among them, mark the index of the temperature factor as 1, mark the index of the humidity factor as 2, mark the index of the wind speed factor as 3, mark the index of the light intensity factor as 4, and mark the index of the electromagnetic interference factor as 5. The constructed judgment matrix is:

[0134]

[0135] Among them, both f and v represent the indices of the evaluation values, where f ∈ [1, 5] and v ∈ [1, 5]. qfv represents the importance of the evaluation value with index f relative to the evaluation value with index v for the environmental parameter evaluation coefficient. The specific value of qfv is determined by relevant experts using the 1 - 9 scoring method. qfv = 9 indicates that the evaluation value with index f is extremely important for the environmental parameter evaluation coefficient compared to the evaluation value with index v, and qfv = 1 indicates that the evaluation value with index f is extremely unimportant for the environmental parameter evaluation coefficient compared to the evaluation value with index v;

[0136] Divide each element value in the judgment matrix by the sum of its column to obtain a normalized judgment matrix. Calculate the mean value of each row element value in the normalized judgment matrix. Take the mean value of the first - row element values as the proportionality coefficient of the temperature factor, the mean value of the second - row element values as the proportionality coefficient of the humidity factor, the wind speed factor as the proportionality coefficient of the corrected nose difference evaluation value, the mean value of the fourth - row element values as the proportionality coefficient of the light intensity factor, and the mean value of the fifth - row element values as the proportionality coefficient of the electromagnetic interference factor. With the constraint that the sum of the scaled - down values equals 1, perform equal - proportion scaling on the five proportionality coefficients, and take the scaled - down values as the weights of the corresponding factors;

[0137] 2.3) Based on the quality evaluation characteristics, generate a point - cloud quality evaluation coefficient for evaluating the quality of the sub - point - cloud data collected by the UAV. The calculation formula is as follows:

[0138]

[0139] In the formula, DYpg is the point - cloud quality evaluation coefficient, which evaluates the quality of the collected sub - point - cloud data from four aspects: point - cloud density, data coverage rate, sampling precision error, and data integrity. The larger the point - cloud quality evaluation coefficient, the worse the quality of the collected sub - point - cloud data, that is, the lower the credibility of the sub - point - cloud data;

[0140] In the formula, D* and O* are the preset appropriate values of point - cloud density and data coverage rate respectively. The appropriate value of point - cloud density is the point - cloud density suitable for subsequent point - cloud data processing, and its value is determined according to the exploration accuracy of the transmission line. For example, when the exploration accuracy is low, the appropriate value of point - cloud density can be taken as 10 points per square meter; when the exploration accuracy is medium, the appropriate value of point - cloud density can be taken as 20 - 50 points per square meter; when the exploration accuracy is high, the appropriate value of point - cloud density can be taken as 100 points per square meter, which is specifically set according to the actual situation. The appropriate value of data coverage rate generally ranges between 20% - 30% to balance the data point acquisition volume and data point connectivity;

[0141] It should be noted that is used to characterize the deviation degree of the point - cloud density from the appropriate value of point - cloud density. The larger its value, the worse the quality of the collected sub - point - cloud data. Similarly It is used to characterize the deviation degree between the data coverage rate and the appropriate value of the data coverage rate. The larger its value is, the worse the quality of the collected sub-point cloud data. Similarly, the worse the sampling accuracy error is, the worse the quality of the sub-point cloud data. And the higher the data integrity is, the more complete the sub-point cloud data is and the better the quality of the sub-point cloud data. Therefore, a negative sign is used to characterize that the data integrity is negatively correlated with the point cloud quality evaluation coefficient;

[0142] In the formula, γ1, γ2, γ3, and γ4 are the weights of the point cloud density, data coverage rate, sampling accuracy error, and data integrity respectively in the calculation of the point cloud quality evaluation coefficient, and the specific values of γ1, γ2, γ3, and γ4 are also determined by the analytic hierarchy process, which will not be elaborated here;

[0143] 2.4) Generate a confidence level based on the flight state evaluation coefficient, environmental parameter evaluation coefficient, quality evaluation coefficient, and the acquisition time interval between the current point cloud data and the original point cloud data. The calculation formula is as follows:

[0144]

[0145] In the formula, ZXD is the confidence level of the sub-point cloud data. It combines the flight state evaluation coefficient, environmental parameter evaluation coefficient, quality evaluation coefficient, and the acquisition time interval between the current point cloud data and the original point cloud data to comprehensively evaluate the credibility of the sub-point cloud data. And the larger the confidence level is, the worse the credibility of the sub-point cloud data;

[0146] It should be noted that the flight state evaluation coefficient, environmental parameter evaluation coefficient, and quality evaluation coefficient evaluate the credibility of the sub-point cloud data from different levels. Therefore, the method of taking the reciprocal of the weighted sum of the three is used to generate the main part of the confidence level. And the larger the three evaluation coefficients are, the worse the credibility of the sub-point cloud data and the smaller the confidence level. χ1, χ2, and χ3 are the weights of the flight state evaluation coefficient, environmental parameter evaluation coefficient, and quality evaluation coefficient respectively in the confidence level evaluation calculation. And because the quality evaluation coefficient directly reflects the quality of the sub-point cloud data, the largest weight is given to it. While the flight state evaluation coefficient and environmental parameter evaluation coefficient both indirectly evaluate and predict the quality of the sub-point cloud data from the external environment, so the same weight is given to the two. Thus, on the basis of χ1 + χ2 + χ3 = 1, let χ3 > χ1 = χ2, and the specific values of the three are debugged and used by the staff according to the actual situation on this basis, and there are not too many restrictions here;

[0147] It should be noted that the original point cloud data is the point cloud data currently in use (i.e., the point cloud data to be updated). The transmission line itself will change continuously with the external environment. Therefore, it is necessary to update the original point cloud data in a timely manner. Moreover, as the time of non-update increases, the necessity and urgency of updating the original point cloud data also increase. Therefore, the acquisition time interval between the current point cloud data and the original point cloud data is introduced to correct the main part of the confidence level. In the formula, t is the acquisition time interval between the current point cloud data and the original point cloud data, and t0 is the preset update time interval threshold. The larger the ratio of t to t0, the higher the degree of urgency to update the original point cloud data. Therefore, the ratio of t to t0 is introduced to correct the main part of the confidence level, so that the finally obtained confidence level takes into account this factor of update urgency. The specific value of the update time interval threshold is set by the staff according to the actual situation, such as set to 1 day, 3 days, etc., which is not restricted here;

[0148] S5. Update the original point cloud data based on the confidence level and the sub-point cloud data. The specific update method is as follows:

[0149] 3.1) Obtain multiple test transmission line areas, and successively collect point cloud data for the test transmission line areas based on the unmanned aerial vehicle. Take the point cloud data obtained in the previous time as the test original point cloud data, and take the point cloud data obtained in the later time as the test current point cloud data. When collecting the test current point cloud data, collect the test actual point cloud data of the test transmission line area based on the ground facilities on the spot, and register the test original point cloud data, the test current point cloud data and the test actual point cloud data based on the iterative closest point algorithm, and calculate the confidence level of the test current point cloud data based on the same method;

[0150] It should be noted that high-precision terrestrial laser scanners (TLS) are selected as the ground facilities to collect the test actual point cloud data of the test transmission line area. Compared with the unmanned aerial vehicle flying in the air, the acquisition environment of the terrestrial laser scanner is more stable, so as to ensure the authenticity and accuracy of the point cloud data collection. And a high-precision GPS receiver and IMU (inertial measurement unit) are configured to improve the spatial positioning accuracy of the point cloud data. During the collection process, the method of step-by-step scanning and multi-angle collection is adopted to ensure that the test actual point cloud data is accurate data that fits the real situation;

[0151] 3.2) Build a point cloud update model based on the convolutional neural network. Use the registered test original point cloud data, the test current point cloud data and their corresponding confidence levels as the input, and use the registered test actual point cloud data as the output to train the point cloud update model. The specific training process is as follows:

[0152] The registered original test point cloud data, the current test point cloud data, and their corresponding confidence levels are combined to form input features. The registered actual test point cloud data is marked on the corresponding input features one by one. The input features after marking are combined to form a data set, and the data set is randomly divided into a training set and a test set according to a ratio of 80 to 20. The training set is used to train the point cloud update model. During the training process, the mean square error is used as the loss function, and the model parameters are iteratively optimized by minimizing the difference between the model prediction value and the actual value. Cross-validation is used to select the optimal model hyperparameters to avoid overfitting. After reaching the predetermined number of iterations, the test set is used to test the processing time estimation model. If the test requirements are met, it is considered that the training is completed; otherwise, the training is restarted until the test requirements are met. The specific test requirements can be set to the accuracy of the model prediction value not less than 80%, 85%, 90%, etc., which is not limited here;

[0153] 3.3) Extract the corresponding sub-point cloud data to be updated from the original point cloud data based on the sub-point cloud data, register the sub-point cloud data and the sub-point cloud data to be updated, and input the registered sub-point cloud data to be updated, the sub-point cloud data, and their corresponding confidence levels into the point cloud update model to obtain the updated sub-point cloud data. The updated sub-point cloud data is input into the original point cloud data to replace the sub-point cloud data to be updated.

[0154] Embodiment 2:

[0155] Please refer to Figure 2 , the present invention provides a transmission line point cloud data update system based on dynamic collection by an unmanned aerial vehicle, which is used for the transmission line point cloud data update method based on dynamic collection by an unmanned aerial vehicle in the above Embodiment 1, including:

[0156] A data acquisition module, based on a predetermined flight route, uses an unmanned aerial vehicle to collect the current point cloud data of the transmission line, and real-time obtains the flight parameters and environmental parameters of the unmanned aerial vehicle during the collection process. The flight parameters include flight coordinates, flight altitude, and flight speed, and the environmental parameters include temperature, humidity, wind speed, light intensity, and electromagnetic interference power density;

[0157] A feature extraction module, which is used to segment the current point cloud data to obtain a plurality of sub-point cloud data, and extract features of the flight parameters and environmental parameters during the collection process of the sub-point cloud data to obtain flight parameter features and environmental parameter features. The flight parameter features include the mean values of flight altitude and flight speed, the deviation values of flight coordinates, flight altitude, and flight speed, and the flight speed fluctuation value. The environmental parameter features include the mean values of temperature, humidity, wind speed, light intensity, and electromagnetic interference power density;

[0158] A feature prediction module, which is used to construct and train a point cloud quality feature extraction model with flight parameter features and environmental parameter features as inputs and quality assessment features as outputs, and input the flight parameter features and environmental parameter features of the sub-point cloud data into the model to obtain quality assessment features. The quality assessment features include the point cloud density, data coverage rate, sampling precision error, and data integrity of the sub-point cloud data;

[0159] A confidence calculation module, which generates a confidence level based on the flight parameter features, environmental parameter features, quality assessment features, and the time interval between the acquisition times of the current point cloud data and the original point cloud data. The confidence level is used to comprehensively evaluate the reliability of the sub-point cloud data;

[0160] A point cloud update module, which updates the original point cloud data based on the confidence level and the sub-point cloud data.

[0161] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by software simulation of a large amount of collected data to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0162] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0163] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0164] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered within the protection scope of the present application.

Claims

1. A method for updating point cloud data of power transmission lines based on dynamic collection by unmanned aerial vehicles, characterized in that: The specific steps include: S1, based on the established flight route, uses drones to collect current point cloud data of the transmission line, and obtains the flight parameters and environmental parameters of the drone in real time during the collection process. The flight parameters include flight coordinates, flight altitude and flight speed, and the environmental parameters include temperature, humidity, wind speed, light intensity and electromagnetic interference power density; S2, segmenting the current point cloud data to obtain a plurality of sub-point cloud data, and extracting features of the flight parameters and environmental parameters in the process of collecting the sub-point cloud data to obtain flight parameter features and environmental parameter features, wherein the flight parameter features include the mean of the flight altitude and the flight speed, the flight coordinates, the deviation value of the flight altitude and the flight speed, and the flight speed fluctuation value, and the environmental parameter features include the mean of temperature, humidity, wind speed, light intensity, and electromagnetic interference power density; S3, constructing and training a point cloud quality feature extraction model whose input is flight parameter features and environmental parameter features and whose output is quality assessment features, inputting the flight parameter features and environmental parameter features of the sub-point cloud data into the model to obtain quality assessment features, the quality assessment features including point cloud density, data coverage, sampling precision error and data integrity of the sub-point cloud data; S4, based on flight parameter characteristics, environmental parameter characteristics, quality assessment characteristics, and the acquisition time interval between the current point cloud data and the original point cloud data, generates confidence, which is used to comprehensively evaluate the reliability of the sub-point cloud data; S5, based on the confidence and the sub-point cloud data, the original point cloud data is updated.

2. The method for updating power transmission line point cloud data based on dynamic collection by unmanned aerial vehicles according to claim 1 is characterized in that: The mean calculation formula of the flight altitude and the flight speed is as follows: In the formula, H(i) and V(i) respectively represent the flight altitude and flight speed of the UAV at the i-th acquisition moment in the process of collecting sub-point cloud data. They represent the mean flight height and the mean flight speed of the UAV in the process of collecting sub-point cloud data, respectively. i is the index of the collection time of the UAV in the process of collecting sub-point cloud data, and i∈[1,m], m is the total number of collection times of the UAV in the process of collecting sub-point cloud data; The calculation formula of the flight coordinate deviation value is as follows: In the formula, lon(i) and lat(i) respectively represent the longitude and latitude of the position of the drone at the i-th acquisition moment in the process of collecting sub-point cloud data. The longitude lon(i) and the latitude lat(i) together constitute the flight coordinates of the drone. lon b (i) lat b (i) respectively represents the longitude and latitude of the position that the UAV should be at according to the established flight route at the i-th acquisition moment in the process of collecting sub-point cloud data, Δlon(i) and Δlat(i) respectively represent the longitude difference and latitude difference between the position of the UAV at the i-th acquisition moment and the position that it should be at during the process of collecting sub-point cloud data; In the formula, dlon(i) and dlat(i) respectively represent the longitude deviation distance and latitude deviation distance between the position of the UAV at the i-th acquisition moment and the position it should be at during the collection of sub-point cloud data, and Cpc represents the flight coordinate deviation value of the UAV during the collection of sub-point cloud data; The calculation formula of the flight altitude deviation value is as follows: In the formula, H(i), H b (i) respectively represent the flight altitude of the UAV at the i-th acquisition moment and the flight altitude of the position according to the established flight route during the process of collecting sub-point cloud data, and Hpc represents the flight altitude deviation value of the UAV during the process of collecting sub-point cloud data; The calculation formula of the flight speed deviation value is as follows: Where, V(i), V b (i) respectively represent the flight speed of the UAV at the i-th acquisition moment and the flight speed at the position according to the established flight route during the process of collecting sub-point cloud data, and Vpc represents the flight speed deviation value of the UAV during the process of collecting sub-point cloud data; The calculation formula of the flight speed fluctuation value is as follows: In the formula, Vbd represents the flight speed fluctuation value of the human-machine during the process of collecting sub-point cloud data; The mean calculation formula of the temperature, humidity, wind speed, light intensity and electromagnetic interference power density is as follows: Where, T(i), RH(i), V f (i), I(i), and E(i) respectively represent the temperature, humidity, wind speed, light intensity, and electromagnetic interference power density of the environment at the i-th acquisition moment when the drone is collecting sub-point cloud data. They respectively represent the mean temperature, humidity, wind speed, light intensity and electromagnetic interference power density of the environment in which the drone is located when collecting sub-point cloud data.

3. The method for updating power transmission line point cloud data based on dynamic collection by unmanned aerial vehicles according to claim 2 is characterized in that: The process of obtaining the quality assessment features of sub-point cloud data is as follows: 1.1) Acquire multiple sample point cloud data with known quality assessment features, flight parameter features and environmental parameter features, and construct parameter feature vectors of each sample point cloud data based on the flight parameter features and environmental parameter features; The method for obtaining the quality assessment features of the sample point cloud data is as follows: Where D represents the point cloud density, N represents the number of data points in the point cloud data, A represents the area covered by the point cloud data, O represents the data coverage rate, Ltotal is the coverage length planned when collecting point cloud data, Loverlap is the length of the overlapping part in the point cloud data, Δxk, Δyk, Δzk are the horizontal distance, vertical distance, and depth distance of the kth reference point and the sampling point corresponding to the reference point in the point cloud data, respectively, k is the index of the reference point, and k∈[1,K], K is the number of reference points, CYwc is the sampling accuracy error, Nth is the expected number of data points corresponding to the point cloud data, and WZpg is the data integrity of the point cloud data; 1.2) Based on the deep neural network, a point cloud quality feature extraction model is constructed, whose input is the parameter feature vector and output is the quality assessment feature. The parameter feature vector of the sample point cloud data is used as the input, and the corresponding quality assessment feature is used as the output label to train the point cloud quality feature extraction model; 1.3) The flight parameter features and environmental parameter features of the sub-point cloud data are concatenated to form a parameter feature vector, and the parameter feature vector is then input into the trained point cloud quality feature extraction model to obtain the quality assessment features of the sub-point cloud data.

4. The method for updating power transmission line point cloud data based on dynamic collection by unmanned aerial vehicles according to claim 3 is characterized in that: The confidence calculation process includes the following steps: 2.1) Based on the flight parameter characteristics, a flight status evaluation coefficient is generated to evaluate the quality of the UAV's flight status when collecting sub-point cloud data. The calculation formula is as follows: Where FXpg is the flight status assessment coefficient, is the preset flight speed deviation threshold, is the preset flight coordinate deviation threshold, ω1, ω2, ω3 are the weights of the flight altitude factor, the flight speed factor and the flight coordinate factor in the calculation of the flight state evaluation coefficient, and ω1+ω2+ω3=1, and ω2>ω1=ω3; 2.2) Based on the environmental parameter characteristics, an environmental parameter evaluation coefficient is generated to evaluate the quality of the environmental parameters of the drone when collecting sub-point cloud data. The calculation formula is as follows: Where HJpg is the environmental parameter assessment coefficient, are the suitable working temperature, suitable working humidity, standard wind resistance value, suitable light intensity and standard anti-electromagnetic interference value when the UAV collects point cloud data, respectively; λ1, λ2, λ3, λ4 and λ5 are the weights of temperature factor, humidity factor, wind speed factor, light intensity factor and electromagnetic interference factor in the calculation of environmental parameter evaluation coefficient, respectively; and the specific values ​​of λ1, λ2, λ3, λ4 and λ5 are determined by the hierarchical analysis method; 2.3) Based on the quality assessment features, a point cloud quality assessment coefficient is generated to evaluate the quality of the sub-point cloud data collected by the drone. The calculation formula is as follows: Where DYpg is the point cloud quality assessment coefficient, D* and O* are the preset suitable values ​​of point cloud density and data coverage, γ1, γ2, γ3, and γ4 are the weights of point cloud density, data coverage, sampling accuracy error, and data integrity in the calculation of point cloud quality assessment coefficient, and the specific values ​​of γ1, γ2, γ3, and γ4 are also determined by the hierarchical analysis method. 2.4) Generate confidence based on the flight status assessment coefficient, environmental parameter assessment coefficient, quality assessment coefficient, and the collection time interval between the current point cloud data and the original point cloud data. The calculation formula is as follows: Where ZXD is the confidence of the sub-point cloud data, χ1, χ2, and χ3 are the weights of the flight status assessment coefficient, environmental parameter assessment coefficient, and quality assessment coefficient in the confidence assessment calculation, respectively, and χ1+χ2+χ3=1, and χ3>χ1=χ2, t is the collection time interval between the current point cloud data and the original point cloud data, and t0 is the preset update time interval threshold.

5. The method for updating power transmission line point cloud data based on dynamic collection by unmanned aerial vehicles according to claim 1 is characterized in that: The method for updating the original point cloud data is as follows: 3.1) Acquire multiple test transmission line areas, and collect point cloud data of the test transmission line areas in sequence based on drones, use the point cloud data obtained in the previous time as the original point cloud data for the test, and use the point cloud data obtained in the next time as the current point cloud data for the test, and when collecting the current point cloud data for the test, collect the actual point cloud data of the test transmission line area based on ground facilities, and align the original point cloud data for the test, the current point cloud data for the test, and the actual point cloud data for the test based on the iterative closest point algorithm, and calculate the confidence of the current point cloud data for the test based on the same method; 3.2) Building a point cloud update model based on a convolutional neural network, taking the registered original point cloud data for the test, the current point cloud data for the test and their corresponding confidence as input, and taking the registered actual point cloud data for the test as output, so as to train the point cloud update model; 3.3) Based on the sub-point cloud data, the corresponding sub-point cloud data to be updated is extracted from the original point cloud data, and the sub-point cloud data and the sub-point cloud data to be updated are aligned, and the aligned sub-point cloud data to be updated, the sub-point cloud data and its corresponding confidence are input into the point cloud update model together to obtain the updated sub-point cloud data, and the updated sub-point cloud data is input into the original point cloud data to replace the sub-point cloud data to be updated.

6. A transmission line point cloud data updating system based on dynamic collection by drones, used in the transmission line point cloud data updating method based on dynamic collection by drones as described in any one of claims 1 to 5, characterized in that: include: The data acquisition module uses a drone to collect the current point cloud data of the power transmission line based on the established flight route, and obtains the flight parameters and environmental parameters of the drone in real time during the collection process. The flight parameters include flight coordinates, flight altitude and flight speed, and the environmental parameters include temperature, humidity, wind speed, light intensity and electromagnetic interference power density; A feature extraction module is used to segment the current point cloud data to obtain multiple sub-point cloud data, and to extract features of flight parameters and environmental parameters in the process of collecting sub-point cloud data to obtain flight parameter features and environmental parameter features, wherein the flight parameter features include the mean of flight altitude and flight speed, flight coordinates, deviation values ​​of flight altitude and flight speed, and flight speed fluctuation value, and the environmental parameter features include the mean of temperature, humidity, wind speed, light intensity, and electromagnetic interference power density; A feature prediction module is used to construct and train a point cloud quality feature extraction model whose input is flight parameter features and environmental parameter features and whose output is quality assessment features. The flight parameter features and environmental parameter features of the sub-point cloud data are input into the model to obtain quality assessment features. The quality assessment features include point cloud density, data coverage, sampling precision error and data integrity of the sub-point cloud data. The confidence calculation module generates confidence based on flight parameter characteristics, environmental parameter characteristics, quality assessment characteristics, and the collection time interval between the current point cloud data and the original point cloud data. The confidence is used to comprehensively evaluate the reliability of the sub-point cloud data. The point cloud update module updates the original point cloud data based on the confidence and sub-point cloud data.

Images