A Method for Managing Point Cloud Data of Highlighted Buildings Based on Multispectral Images

Abstract

The present invention discloses a method for managing point cloud data of highlighted buildings based on multispectral images, which relates to the technical field of building point cloud data management. The method for managing point cloud data of highlighted buildings based on multispectral images includes the following steps: collecting predefined spectral images of highlighted buildings by using an unmanned aerial vehicle; performing a first comparative analysis on the multispectral point cloud segmentation data of highlighted buildings; performing a first evaluation analysis on the multispectral point cloud segmentation data of highlighted buildings; performing a second evaluation analysis on the multispectral point cloud segmentation data of highlighted buildings; and performing a third point cloud data management process according to the results of the third comparative analysis. Through the regulation of the first and second evaluation analyses and hierarchical comparative analyses, the present invention achieves the effect of improving the accuracy of collecting point cloud data of highlighted buildings in multispectral images at night, and solves the problem of low accuracy of collecting point cloud data of highlighted buildings in multispectral images at night in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of building point cloud data management, and in particular to a method for managing highlighted building point cloud data based on multi-spectral images. Background Art

[0002] With the rapid development of remote sensing technology, high-resolution remote sensing images have become easily accessible. These images possess rich texture information and spectral information, providing favorable features for the discrimination and extraction of buildings, and have been widely applied in the field of building extraction and recognition. At the same time, as a means of real-time acquisition of three-dimensional spatial information, lidar technology is developing at an astonishing speed. Lidar technology effectively broadens the scope of data sources, changes the data acquisition mode, and can quickly acquire point cloud data to construct a high-resolution digital surface model.

[0003] Existing methods for managing highlighted building point cloud data based on multi-spectral images are achieved through the following techniques, including: building detection, using machine learning or deep learning algorithms to detect and identify buildings from the fused data; highlighted building recognition, identifying highlighted buildings according to specific criteria (such as height, reflectivity, etc.); point cloud optimization, optimizing the point cloud data through algorithms to improve its accuracy and quality, and using the point cloud data to reconstruct the three-dimensional surface model of the building; designing an effective data structure to store and manage a large amount of point cloud and multi-spectral image data; using a database management system to store, retrieve, and analyze data; visualization and analysis, using three-dimensional visualization tools to display the point cloud model of the highlighted building.

[0004] For example, the patent application with publication number CN118428737A discloses a method and related equipment for building risk assessment based on InSAR point cloud, including: obtaining multi-track SAR data of the research area, and extracting multi-track InSAR point clouds of multiple buildings in the research area; constructing a point cloud registration loss function to register the multi-track InSAR point clouds, and obtaining the registered multi-track InSAR point clouds of each building among the multiple buildings; constructing a three-dimensional deformation decomposition model, and calculating the multi-dimensional deformation rate and multi-dimensional deformation time series of each building according to the three-dimensional deformation decomposition model and the registered multi-track InSAR point clouds; calculating the deformation characteristic parameters corresponding to each building according to the multi-dimensional deformation rate and multi-dimensional deformation time series; and evaluating the risk level of each building according to the deformation characteristic parameters.

[0005] For example, a method for calculating the large-scale building photovoltaic potential based on airborne point cloud data disclosed in the invention patent application with the publication number of CN118570023A includes: obtaining three-dimensional point cloud data of an urban area through an airborne lidar; performing unsupervised domain adaptation training by using the publicly available three-dimensional point cloud data of the urban area with annotations and the three-dimensional point cloud data to be classified; using the trained deep learning model to perform forward inference on the three-dimensional point cloud data to be classified to obtain the classification result of the point cloud data; extracting the building category point cloud according to the semantic segmentation result, obtaining the single building point cloud data through conditional Euclidean clustering, and performing three-dimensional reconstruction on the single building point cloud data to obtain the building three-dimensional model; performing radiation simulation according to the building three-dimensional model of the area and the nearby weather data, and obtaining the photovoltaic potential of each building according to the solar radiation value.

[0006] However, in the process of implementing the inventive technical solution in the embodiments of the present application, it is found that the above technology has at least the following technical problems:

[0007] In the prior art, for the acquisition of high-brightness building point cloud data in the night environment, some prior arts, such as structured light scanning and other methods, will fail, while other prior arts, such as airborne lidar measurement and other methods, will have greatly reduced effects. Moreover, when the night light is insufficient, the light of the high-brightness building itself is strong, and there is a problem of low accuracy in the acquisition of high-brightness building point cloud data based on multi-spectral images at night. Summary of the Invention

[0008] The embodiments of the present application provide a method for managing high-brightness building point cloud data based on multi-spectral images, which solves the problem of low accuracy in the acquisition of high-brightness building point cloud data based on multi-spectral images in the prior art, and achieves the effect of improving the accuracy of the acquisition of high-brightness building point cloud data based on multi-spectral images at night.

[0009] An embodiment of the present application provides a method for managing high - light building point cloud data based on multi - spectral images, including the following steps: Pre - define spectral image acquisition of high - light buildings through an unmanned aerial vehicle (UAV) to obtain the original multi - spectral image data of high - light buildings and the original lidar data of high - light buildings, and perform pre - processing to obtain the multi - spectral point cloud fusion data of high - light buildings; Divide the multi - spectral point cloud fusion data of high - light buildings according to a pre - defined fusion data size to obtain the multi - spectral point cloud segmentation data of high - light buildings, perform a first comparative analysis on the multi - spectral point cloud segmentation data of high - light buildings, and perform a first point cloud data management process according to the results of the first comparative analysis; Perform a first evaluation analysis on the multi - spectral point cloud segmentation data of high - light buildings to obtain the basic value of the quality fluctuation of the multi - spectral point cloud segmentation of high - light buildings, perform a second comparative analysis according to the basic value of the quality fluctuation of the multi - spectral point cloud segmentation of high - light buildings, and perform a second point cloud data management process according to the results of the second comparative analysis; Perform a second evaluation analysis on the multi - spectral point cloud segmentation data of high - light buildings to obtain the noise correction value of the multi - spectral point cloud segmentation quality of high - light buildings, comprehensively analyze to obtain the comprehensive value of the multi - spectral point cloud segmentation quality of high - light buildings, perform a third comparative analysis according to the comprehensive value of the multi - spectral point cloud segmentation quality of high - light buildings, and perform a third point cloud data management process according to the results of the third comparative analysis.

[0010] Further, the process of obtaining the multi - spectral point cloud fusion data of high - light buildings is as follows: Import the original multi - spectral image data of high - light buildings collected by the UAV into a pre - defined spectral data processing software, and perform radiometric correction, geometric correction, and atmospheric correction on the original multi - spectral image data of high - light buildings through the pre - defined data processing software to obtain the corrected multi - spectral image data of high - light buildings; Import the original lidar data of high - light buildings collected by the UAV into a pre - defined point cloud data processing software, and convert the original lidar data of high - light buildings into point cloud data of high - light buildings and remove abnormal points through the pre - defined point cloud data processing software to obtain the corrected point cloud data of high - light buildings; Perform position data annotation on the corresponding corrected multi - spectral image data of high - light buildings and the corrected point cloud data of high - light buildings according to the position positioning system built in the UAV; Perform data fusion on the corresponding corrected multi - spectral image data of high - light buildings and the corresponding corrected point cloud data of high - light buildings according to the same position data annotation information to obtain the multi - spectral point cloud fusion data of high - light buildings.

[0011] Further, the first comparative analysis on the multi - spectral point cloud segmentation data of high - light buildings specifically includes: Process different multi - spectral point cloud segmentation data of high - light buildings through a pre - defined contrast software to obtain the dispersion degree of different multi - spectral point cloud segmentation data of high - light buildings; Process different multi - spectral point cloud segmentation data of high - light buildings through a pre - defined contrast software to obtain the contrast of different multi - spectral point cloud segmentation data of high - light buildings.

[0012] Further, the first point cloud data management process based on the first comparative analysis result is as follows: If the dispersion degree of the multi-spectral point cloud segmentation data of the highlighted building is less than the dispersion degree threshold of the multi-spectral point cloud segmentation data of the highlighted building and the contrast of the multi-spectral point cloud segmentation data of the highlighted building is less than the contrast threshold of the multi-spectral point cloud segmentation data of the highlighted building, the corresponding segmentation area is recorded as the first point cloud data acquisition area; If the dispersion degree of the multi-spectral point cloud segmentation data of the highlighted building is greater than or equal to the dispersion degree threshold of the multi-spectral point cloud segmentation data of the highlighted building, the corresponding segmentation area is recorded as the second point cloud data acquisition area; If the contrast of the multi-spectral point cloud segmentation data of the highlighted building is greater than or equal to the contrast threshold of the multi-spectral point cloud segmentation data of the highlighted building, the corresponding segmentation area is recorded as the second point cloud data acquisition area; The position point corresponding to the second point cloud data acquisition area is obtained through the position positioning tool built in the UAV. The UAV flies to the corresponding position point to collect data again and makes a loop judgment until the dispersion degree of the multi-spectral point cloud segmentation data of the highlighted building in the loop judgment is less than the dispersion degree threshold of the multi-spectral point cloud segmentation data of the highlighted building, the contrast of the multi-spectral point cloud segmentation data of the highlighted building is less than the contrast threshold of the multi-spectral point cloud segmentation data of the highlighted building, and the number of loop judgments is less than the loop judgment threshold; If the number of loop judgments is greater than or equal to the loop judgment threshold, the corresponding second point cloud data acquisition area is notified to the relevant personnel.

[0013] Further, obtaining the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of the highlighted building specifically includes: Classifying and extracting the multi-spectral point cloud segmentation data of the highlighted building in the first point cloud data acquisition area to obtain the reflectivity, contrast, and radiance of the highlighted building in the first point cloud data acquisition area; The reflectivity of the highlighted building includes the maximum reflectivity of the highlighted building and the minimum reflectivity of the highlighted building; The contrast of the highlighted building includes the maximum contrast of the highlighted building and the minimum contrast of the highlighted building; The standard values of the reflectivity, contrast, and radiance of the highlighted building are directly obtained from the multi-spectral image database of the highlighted building; Analyze to obtain the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of the highlighted building in the first point cloud data acquisition area.

[0014] Further, the second point cloud data management process based on the second comparative analysis result is as follows: If the basic value of the segmentation quality fluctuation of the highlighted building multispectral point cloud is greater than or equal to the threshold value of the segmentation quality fluctuation of the highlighted building multispectral point cloud, the drone reaches the first point cloud data acquisition area through the built-in position positioning system, opens the telescopic light shield and extends the exposure time, and then performs predefined spectral image acquisition, and makes a loop judgment until the basic value of the segmentation quality fluctuation of the highlighted building multispectral point cloud in the loop judgment is less than the threshold value of the segmentation quality fluctuation of the highlighted building multispectral point cloud and the number of loop judgments is less than the loop judgment threshold; If the number of loop judgments is greater than or equal to the loop judgment threshold, the corresponding first point cloud data acquisition area is notified to the relevant personnel; If the basic value of the segmentation quality fluctuation of the highlighted building multispectral point cloud is less than the threshold value of the segmentation quality fluctuation of the highlighted building multispectral point cloud, the first point cloud data acquisition area is recorded as the third point cloud data acquisition area.

[0015] Further, obtaining the noise correction value of the segmentation quality of the highlighted building multispectral point cloud specifically includes: classifying and extracting the segmentation data of the highlighted building multispectral point cloud in the third point cloud data acquisition area to obtain the reflectivity of the surface material of the highlighted building in the third point cloud data acquisition area; The reflectivity of the surface material of the highlighted building includes the maximum value of the reflectivity of the surface material of the highlighted building and the minimum value of the reflectivity of the surface material of the highlighted building; The maximum value of the night ambient light and the minimum value of the night ambient light in the third point cloud data acquisition area are collected through a lux meter; Analyze to obtain the noise correction value of the segmentation quality of the highlighted building multispectral point cloud in the third point cloud data acquisition area.

[0016] Further, the specific process of comprehensively analyzing and obtaining the comprehensive value of the segmentation quality of the highlighted building multispectral point cloud is as follows: Perform a first evaluation and analysis on the segmentation data of the highlighted building multispectral point cloud in the third point cloud data acquisition area to obtain the basic value of the segmentation quality fluctuation of the highlighted building multispectral point cloud in the third point cloud data acquisition area; Obtain the noise correction value of the segmentation quality of the highlighted building multispectral point cloud in the third point cloud data acquisition area; Comprehensively analyze the basic value of the segmentation quality fluctuation of the highlighted building multispectral point cloud and the noise correction value of the segmentation quality of the highlighted building multispectral point cloud in the third point cloud data acquisition area to obtain the comprehensive value of the segmentation quality of the highlighted building multispectral point cloud.

[0017] Further, the third point cloud data management process based on the third comparative analysis result specifically includes: if the comprehensive value of the multi-spectral point cloud segmentation quality of the highlighted building is less than the comprehensive threshold of the multi-spectral point cloud segmentation quality of the highlighted building, no adjustment is made; if the comprehensive value of the multi-spectral point cloud segmentation quality of the highlighted building is greater than or equal to the comprehensive threshold of the multi-spectral point cloud segmentation quality of the highlighted building, the difference between the comprehensive value of the multi-spectral point cloud segmentation quality of the highlighted building and the comprehensive threshold of the multi-spectral point cloud segmentation quality of the highlighted building is recorded as the difference in the multi-spectral point cloud segmentation quality of the highlighted building; if the difference in the multi-spectral point cloud segmentation quality of the highlighted building is less than the difference threshold of the multi-spectral point cloud segmentation quality of the highlighted building, density filtering processing is performed on the multi-spectral point cloud segmentation data of the highlighted building in the corresponding third point cloud data acquisition area; if the difference in the multi-spectral point cloud segmentation quality of the highlighted building is greater than or equal to the difference threshold of the multi-spectral point cloud segmentation quality of the highlighted building, bilateral filtering processing is performed on the multi-spectral point cloud segmentation data of the highlighted building in the corresponding third point cloud data acquisition area.

[0018] Further, the third point cloud data management process based on the third comparative analysis result further includes: the built-in position positioning system of the drone is used to collect data again according to the third point cloud data acquisition area and perform a loop judgment until the comprehensive value of the multi-spectral point cloud segmentation quality of the highlighted building in the loop judgment is less than the comprehensive threshold of the multi-spectral point cloud segmentation quality of the highlighted building and the number of loop judgments is less than the loop judgment threshold; if the number of loop judgments is greater than or equal to the loop judgment threshold, the corresponding third point cloud data acquisition area is notified to relevant personnel.

[0019] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0020] 1. The pre-defined spectral images of the highlighted building are collected by the drone; the first comparative analysis is performed on the multi-spectral point cloud segmentation data of the highlighted building; the first evaluation analysis is performed on the multi-spectral point cloud segmentation data of the highlighted building; the second evaluation analysis is performed on the multi-spectral point cloud segmentation data of the highlighted building; the third point cloud data management process is performed according to the third comparative analysis result. Through the first and second evaluation analyses and hierarchical comparative analysis and regulation, the effect of improving the accuracy of the point cloud data of the highlighted building in the multi-spectral image at night is achieved, and the problem that the accuracy of the point cloud data of the highlighted building based on the multi-spectral image is not high at night in the prior art is solved.

[0021] 2. Perform the second point cloud data management process based on the second comparative analysis result. The specific process is as follows. By real-time monitoring the quality fluctuation of multi-spectral point cloud segmentation and taking corresponding measures when the quality drops, the quality of the collected point cloud data is always maintained at a high level. Utilize the built-in position positioning system of the drone and the predefined acquisition process to achieve the automation of point cloud data acquisition, thereby greatly improving the efficiency of the method for managing highlight building point cloud data based on multi-spectral images.

[0022] 3. Perform the third point cloud data management process according to the third comparative analysis result. By comparing the comprehensive value of the multi-spectral point cloud segmentation quality of highlight buildings with a threshold, the data areas that need further processing can be identified. Then, according to the comparison result between the comprehensive value of the segmentation quality and the threshold, different filtering methods are selected, thereby achieving the robustness of the method for managing highlight building point cloud data based on multi-spectral images. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flowchart of the method for managing highlight building point cloud data based on multi-spectral images provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] By providing a method for managing highlight building point cloud data based on multi-spectral images, the embodiment of the present application solves the problem in the prior art that the accuracy of collecting highlight building point cloud data based on multi-spectral images at night is not high. Through the first and second evaluation analyses and hierarchical comparative analyses for regulation and control, the effect of improving the accuracy of collecting highlight building point cloud data based on multi-spectral images at night is achieved.

[0025] To better understand the above technical solutions, the above technical solutions will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments.

[0026] Such as Figure 1As shown in the figure, it is a flowchart of a method for managing high - light building point cloud data based on multi - spectral images provided by an embodiment of the present application. The method includes the following steps: Pre - define spectral image acquisition of high - light buildings through an unmanned aerial vehicle (UAV) to obtain original data of multi - spectral images of high - light buildings and original data of lidar of high - light buildings, and perform pre - processing to obtain multi - spectral point cloud fusion data of high - light buildings; Divide the multi - spectral point cloud fusion data of high - light buildings according to a pre - defined fusion data size to obtain segmented multi - spectral point cloud data of high - light buildings, perform a first comparative analysis on the segmented multi - spectral point cloud data of high - light buildings, and perform a first point cloud data management process according to the results of the first comparative analysis; Perform a first evaluation analysis on the segmented multi - spectral point cloud data of high - light buildings to obtain a basic value of the quality fluctuation of the segmented multi - spectral point cloud of high - light buildings, perform a second comparative analysis according to the basic value of the quality fluctuation of the segmented multi - spectral point cloud of high - light buildings, and perform a second point cloud data management process according to the results of the second comparative analysis; Perform a second evaluation analysis on the segmented multi - spectral point cloud data of high - light buildings to obtain a noise correction value of the quality of the segmented multi - spectral point cloud of high - light buildings, comprehensively analyze to obtain a comprehensive value of the quality of the segmented multi - spectral point cloud of high - light buildings, perform a third comparative analysis according to the comprehensive value of the quality of the segmented multi - spectral point cloud of high - light buildings, and perform a third point cloud data management process according to the results of the third comparative analysis.

[0027] Further, the process of obtaining the multi - spectral point cloud fusion data of high - light buildings is as follows: Import the original data of multi - spectral images of high - light buildings collected by the UAV into a pre - defined spectral data processing software, and perform radiometric correction, geometric correction, and atmospheric correction on the original data of multi - spectral images of high - light buildings through the pre - defined data processing software to obtain corrected data of multi - spectral images of high - light buildings; Import the original lidar data of high - light buildings collected by the UAV into a pre - defined point cloud data processing software, and convert the original lidar data of high - light buildings into point cloud data of high - light buildings and remove abnormal points through the pre - defined point cloud data processing software to obtain corrected point cloud data of high - light buildings; Perform position data annotation on the corresponding corrected multi - spectral image data of high - light buildings and corrected point cloud data of high - light buildings according to the position positioning system built in the UAV; Perform data fusion on the corresponding corrected multi - spectral image data of high - light buildings and the corresponding corrected point cloud data of high - light buildings according to the same position data annotation information to obtain multi - spectral point cloud fusion data of high - light buildings.

[0028] In this embodiment, the specific acquisition angle and height of the UAV are pre - defined settings and change according to specific settings.

[0029] The original data of multi - spectral images of high - light buildings collected has GPS position annotation.

[0030] Radiometric correction is performed on the image to eliminate the influence of the sensor and atmospheric conditions on the image and ensure the consistency of the radiometric measurement of the image. Geometric correction is performed on the image to eliminate the image distortion caused by the change in the flight attitude of the drone. Atmospheric correction is performed on the image to reduce the influence of atmospheric scattering and absorption on the image and restore the true reflectance of the ground objects.

[0031] The predefined spectral data processing software is ENVI or ERDAS.

[0032] Use the radiometric calibration parameters provided by the sensor: First, convert the digital values of the image into radiance values using the radiometric calibration coefficients (including gain and offset) provided by the sensor manufacturer. This process is called radiometric calibration. Use the conversion formula to convert the original data of the multi-spectral image of the highlighted building into radiance values.

[0033] Use the data of the radiometric standard plate for further calibration: If available, use the data of the radiometric standard plate (e.g., a laboratory-calibrated radiation source or a radiometric reference plate set up on-site) to further calibrate the image. The radiometric standard plate provides a known and stable radiance or reflectance value, which can be used as a reference to obtain the radiometric correction data of the multi-spectral image of the highlighted building.

[0034] For geometric correction, select or import ground control points, and use geometric correction algorithms (such as polynomial transformation, affine transformation, etc.) to correct the radiometric correction data of the multi-spectral image of the highlighted building according to the GCPs to obtain the geometric correction data of the multi-spectral image of the highlighted building.

[0035] For atmospheric correction, input the parameters required for atmospheric correction, such as imaging time, geographical location, altitude, and atmospheric conditions, and select the 6S model as the atmospheric correction model.

[0036] Run the atmospheric correction algorithm to generate the corrected image and obtain the correction data of the multi-spectral image of the highlighted building.

[0037] Use the lidar system carried by the drone for data acquisition. The lidar system emits laser pulses and receives the optical signals reflected from the building surface; the lidar calculates the distance to the object by emitting laser pulses and measuring the return time, thereby generating three-dimensional point cloud data.

[0038] The lidar data is synchronized with the global positioning system and inertial measurement unit data on the drone for subsequent geolocation and attitude correction. The original lidar data of the highlighted building collected has GPS position markings.

[0039] Preprocess the collected lidar data, including removing invalid points, correcting the lidar scanning angle and distance deviation, etc. This is achieved through the built-in software of the lidar.

[0040] Use predefined point cloud data processing software, such as PDAL (Point Data Abstraction Library), to convert the preprocessed lidar data into point cloud data.

[0041] Export the processed point cloud data into a standard format, such as LAS. LAS is an open standard format used for the exchange of lidar (LiDAR) data in the U.S. Geographic Information System. The LAS file format is developed by ASPRS (American Society for Photogrammetry and Remote Sensing) and has become the de facto standard for LiDAR data exchange.

[0042] Perform data fusion on the corresponding highlighted building multispectral image correction data and the corresponding highlighted building point cloud correction data according to the same position data annotation information, specifically including:

[0043] Project the multispectral image data into the space of the point cloud data. This is achieved by mapping the image pixels to the corresponding points in the point cloud.

[0044] For each point in the point cloud, find its corresponding pixel in the multispectral image and assign the color information of that pixel to the point in the point cloud.

[0045] If some points in the point cloud do not have corresponding pixels in the multispectral image, interpolation methods (such as nearest neighbor interpolation, bilinear interpolation, etc.) are used to estimate the colors of these points.

[0046] Fuse the point cloud data and the multispectral image data together to form a point cloud data set containing three-dimensional geometric information and multispectral color information.

[0047] Furthermore, perform a first comparative analysis on the highlighted building multispectral point cloud segmentation data, specifically including: processing different highlighted building multispectral point cloud segmentation data through predefined contrast software to obtain the dispersion degree of different highlighted building multispectral point cloud segmentation data; processing different highlighted building multispectral point cloud segmentation data through predefined contrast software to obtain the contrast of different highlighted building multispectral point cloud segmentation data.

[0048] In this embodiment, calculate the standard deviation of the point coordinates in the highlighted building multispectral point cloud segmentation data. The standard deviation reflects the dispersion degree of the point coordinate distribution. Select the points in the point cloud data that are known to be uniform or low-texture regions for calculation. These regions usually contain less structural information, so the influence of noise is more obvious. In the environment of highlighted buildings at night, the lights are default selected as the points for calculating the point coordinates in the highlighted building multispectral point cloud segmentation data.

[0049] Process through predefined contrast software. For example, use the Pandas library and NumPy library in Python to calculate the dispersion degree of point cloud data.

[0050] import pandas as pd

[0051] import numpy as np

[0052] # Read point cloud data

[0053] point_cloud_data = pd.read_csv('point_cloud_data.csv')

[0054] # Select one or more bands for noise analysis

[0055] # For example, select X, Y, Z coordinates

[0056] x = point_cloud_data['X']

[0057] y = point_cloud_data['Y']

[0058] z = point_cloud_data['Z']

[0059] # Select one or more regions to calculate the noise level

[0060] # For example, select a small region in the center of the point cloud data

[0061] region_of_interest = point_cloud_data[(point_cloud_data['X'] > 100) & (point_cloud_data['X'] < 200) & (point_cloud_data['Y'] > 100) & (point_cloud_data['Y'] < 200) & (point_cloud_data['Z'] > 100) & (point_cloud_data['Z'] < 200)]

[0062] # Calculate the dispersion degree

[0063] noise_level_x = np.std(region_of_interest['X'])

[0064] noise_level_y = np.std(region_of_interest['Y'])

[0065] noise_level_z = np.std(region_of_interest['Z'])

[0066] Processed by predefined contrast software. For example, use the Pandas library and NumPy library in Python to calculate the contrast of point cloud data.

[0067] import pandas as pd

[0068] Import numpy as np

[0069] # Read point cloud data

[0070] point_cloud_data = pd.read_csv('point_cloud_data.csv')

[0071] # Select one or more bands for contrast analysis

[0072] # For example, select X, Y, Z coordinates

[0073] x = point_cloud_data1['X']

[0074] y = point_cloud_data2['Y']

[0075] z = point_cloud_data3['Z']

[0076] # Calculate the brightness difference between adjacent points in the point cloud. For example, calculate the contrast of the X coordinate

[0077] contrast_x = np.abs(np.diff(x))

[0078] Through the call of Python software, the dispersion degree and contrast can be quickly analyzed.

[0079] Further, perform first point cloud data management processing according to the first comparative analysis result. The specific process is as follows: If the dispersion degree of the highlighted building multispectral point cloud segmentation data is less than the dispersion degree threshold of the highlighted building multispectral point cloud segmentation data and the contrast of the highlighted building multispectral point cloud segmentation data is less than the contrast threshold of the highlighted building multispectral point cloud segmentation data, then mark the corresponding segmentation area as the first point cloud data acquisition area; if the dispersion degree of the highlighted building multispectral point cloud segmentation data is greater than or equal to the dispersion degree threshold of the highlighted building multispectral point cloud segmentation data, then mark the corresponding segmentation area as the second point cloud data acquisition area; if the contrast of the highlighted building multispectral point cloud segmentation data is greater than or equal to the contrast threshold of the highlighted building multispectral point cloud segmentation data, then mark the corresponding segmentation area as the second point cloud data acquisition area; obtain the position points corresponding to the second point cloud data acquisition area through the position positioning tool built in the drone, and the drone flies to the corresponding position points to collect data again and make a loop judgment until the dispersion degree of the highlighted building multispectral point cloud segmentation data in the loop judgment is less than the dispersion degree threshold of the highlighted building multispectral point cloud segmentation data, the contrast of the highlighted building multispectral point cloud segmentation data is less than the contrast threshold of the highlighted building multispectral point cloud segmentation data, and the loop judgment times are less than the loop judgment threshold; if the loop judgment times are greater than or equal to the loop judgment threshold, then notify the relevant personnel of the corresponding second point cloud data acquisition area.

[0080] In this embodiment, if the loop judgment times are greater than or equal to the loop judgment threshold, it means that in the actual situation, it is possible that the strong light of a building just shines on the second point cloud data acquisition area, or most of the rooms in the building at night have no lights, only a few lights, making the contrast of the spectrum in the area obvious, so that the highlighted building multispectral point cloud segmentation data collected by the drone is always at a low quality level.

[0081] Further, obtain the basic value of the quality fluctuation of the highlighted building multispectral point cloud segmentation, which specifically includes: classifying and extracting the highlighted building multispectral point cloud segmentation data in the first point cloud data acquisition area to obtain the highlighted building reflectivity, highlighted building contrast, and highlighted building radiation brightness in the first point cloud data acquisition area; the highlighted building reflectivity includes the maximum value of the highlighted building reflectivity and the minimum value of the highlighted building reflectivity; the highlighted building contrast includes the maximum value of the highlighted building contrast and the minimum value of the highlighted building contrast; directly obtain the standard value of the highlighted building reflectivity, the standard value of the highlighted building contrast, and the standard value of the highlighted building radiation brightness from the highlighted building multispectral image database; analyze and obtain the basic value of the quality fluctuation of the highlighted building multispectral point cloud segmentation in the first point cloud data acquisition area.

[0082] In this embodiment, for the classification and extraction of the multi-spectral point cloud segmentation data of highlighted buildings in the first point cloud data acquisition area, a specific example is as follows: Calculate the reflectivity for each point of the multi-spectral point cloud segmentation data of highlighted buildings, usually by comparing the intensities of the incident light and the reflected light. Calculate the contrast of the highlighted building area, usually by comparing the reflectivity differences of adjacent points in the multi-spectral point cloud segmentation data of highlighted buildings. Obtain the radiance of each point in the multi-spectral point cloud segmentation data of highlighted buildings, which is usually obtained through sensor calibration and atmospheric correction to analyze the distribution of radiance to determine the radiation characteristics of highlighted buildings.

[0083] The basic value of the quality fluctuation of the multi-spectral point cloud segmentation of highlighted buildings is used to describe the negative degree level of the impact of highlighted buildings by the quality of multi-spectral point cloud acquisition.

[0084] Number the first point cloud data acquisition area. Represents the number of the first point cloud data acquisition area. Represents the total number of the numbers of the first point cloud data acquisition area.

[0085] Divide the point cloud data detection time into different point cloud data detection time periods according to the size of the predefined point cloud data detection time window, and number the point cloud data detection time periods. Represents the number of the point cloud data detection time period. Represents the total number of the numbers of the point cloud data detection time periods.

[0086] Represents the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of highlighted buildings in the

[0087] ;

[0088] Represents the natural constant;

[0089] Represents the maximum value of the reflectivity of highlighted buildings in the th point cloud data detection time period in the

[0090] Represents the minimum value of the reflectivity of highlighted buildings in the th point cloud data detection time period in the

[0091] Represents the maximum value of the reflectivity of highlighted buildings in the The standard value of the reflectivity of highlighted buildings for a point cloud data detection time period. The standard value of the reflectivity of highlighted buildings is directly obtained from the multi-spectral image database of highlighted buildings.

[0092] Indicates the th maximum value of the contrast of highlighted buildings for the th point cloud data detection time period in the first point cloud data acquisition area.

[0093] Indicates the th minimum value of the contrast of highlighted buildings for the th point cloud data detection time period in the first point cloud data acquisition area.

[0094] Indicates the th standard value of the contrast of highlighted buildings for the th point cloud data detection time period in the first point cloud data acquisition area. The standard value of the contrast of highlighted buildings is directly obtained from the multi-spectral image database of highlighted buildings.

[0095] Indicates the th radiance of highlighted buildings for the th point cloud data detection time period in the first point cloud data acquisition area.

[0096] Indicates the th standard value of the radiance of highlighted buildings in the first point cloud data acquisition area. The standard value of the radiance of highlighted buildings is directly obtained from the multi-spectral image database of highlighted buildings.

[0097] The radiance of highlighted buildings may be abnormally high, which may be caused by too high reflectivity or sensor saturation. Some building materials (such as glass, reflective metal plates, etc.) have very high reflectivity, which will cause a large amount of solar radiation to be reflected at specific angles and lighting conditions.

[0098] Indicates the weight factor of the difference between the maximum value and the minimum value of the reflectivity of highlighted buildings for the basic value of the quality fluctuation of multi-spectral point cloud segmentation of highlighted buildings, indicating the influence degree of the maximum value of the reflectivity of highlighted buildings on the basic value of the quality fluctuation of multi-spectral point cloud segmentation of highlighted buildings.

[0099] Indicates the weight factor of the difference between the maximum value and the minimum value of the contrast of highlighted buildings for the basic value of the quality fluctuation of multi-spectral point cloud segmentation of highlighted buildings, indicating the influence degree of the maximum value of the contrast of highlighted buildings on the basic value of the quality fluctuation of multi-spectral point cloud segmentation of highlighted buildings.

[0100] The weight factor of the maximum reflectivity of the highlighted building for the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of the highlighted building and the weight factor of the maximum contrast of the highlighted building for the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of the highlighted building are directly obtained from the multi-spectral image database of the highlighted building through a preset mapping relationship.

[0101] Use a lux meter to directly measure the light intensity at a specific location. The lux meter can measure the luminous flux per unit area. For example, construct a mapping set of the ambient light illumination intensity and the corresponding weight factor of the maximum reflectivity of the highlighted building for the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of the highlighted building and the weight factor of the maximum contrast of the highlighted building for the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of the highlighted building, and input the real-time ambient light illumination intensity into the mapping set to obtain the weight factor of the maximum reflectivity of the highlighted building for the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of the highlighted building and the weight factor of the maximum contrast of the highlighted building for the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of the highlighted building, where the mapping relationship is a one-to-one or many-to-one relationship.

[0102] Denote the sensor resolution error factor. The spatial resolution of the sensor affects the detail level of the point cloud. It is obtained from the multi-spectral image database of the highlighted building through a preset mapping relationship.

[0103] Atmospheric transmittance describes the energy loss when light passes through the atmosphere. The lower the transmittance, the stronger the absorption and scattering of light by the atmosphere.

[0104] Denote the th atmospheric transmittance of the th point cloud data detection time period in the

[0105] Denote the th atmospheric transmittance standard value of the th point cloud data detection time period in the

[0106] By using an atmospheric radiative transfer model to simulate the propagation process of light waves in the atmosphere to calculate the atmospheric transmittance.

[0107] Example steps to obtain the transmittance using an atmospheric model:

[0108] Select a suitable radiative transfer model: Select the model according to the wavelength range and accuracy requirements to be simulated.

[0109] Input atmospheric parameters: including but not limited to aerosol type, aerosol optical depth (AOD), water vapor content, ozone content, surface pressure, temperature, etc.

[0110] Set the observation geometry: including the zenith angle and azimuth angle of the sun and the observer, etc.

[0111] Run the model: The model will calculate the propagation path of light waves in the atmosphere based on the input parameters and give the transmittance.

[0112] Output results: The model will output the transmittance value of a specific wavelength or band.

[0113] Furthermore, perform the second point cloud data management process according to the second comparative analysis result. The specific process is as follows: If the basic value of the multi-spectral point cloud segmentation quality fluctuation of the highlighted building is greater than or equal to the threshold value of the multi-spectral point cloud segmentation quality fluctuation of the highlighted building, the drone will reach the first point cloud data acquisition area through the built-in position positioning system, open the telescopic light shield and extend the exposure time, and then perform predefined spectral image acquisition, and make a loop judgment until the basic value of the multi-spectral point cloud segmentation quality fluctuation of the highlighted building in the loop judgment is less than the threshold value of the multi-spectral point cloud segmentation quality fluctuation of the highlighted building and the number of loop judgments is less than the loop judgment threshold; if the number of loop judgments is greater than or equal to the loop judgment threshold, notify the relevant personnel of the corresponding first point cloud data acquisition area; if the basic value of the multi-spectral point cloud segmentation quality fluctuation of the highlighted building is less than the threshold value of the multi-spectral point cloud segmentation quality fluctuation of the highlighted building, the first point cloud data acquisition area is recorded as the third point cloud data acquisition area.

[0114] In this embodiment, under night conditions, the reflectance is still obtained in spectral analysis, but some special factors need to be considered. The lighting conditions at night are different from those during the day and mainly rely on moonlight, artificial light sources (such as street lights, building lighting, etc.) and scattered light in the environment. The intensity and spectral characteristics of these light sources are significantly different from those of sunlight, including: The light sources at night may have different spectral distributions, which will affect the measurement of reflectance. It is necessary to understand the spectral characteristics of the light sources for accurate measurement and correction. The lighting intensity at night is usually low, which may lead to a decrease in the signal-to-noise ratio of reflectance measurement. Therefore, it may be necessary to extend the exposure time to obtain sufficient light signals. The ambient light at night may include scattered light from surrounding objects, which may interfere with the measurement of reflectance. It is necessary to take measures to reduce these interferences, such as using a light shield.

[0115] Further, obtain the noise correction value for the multi-spectral point cloud segmentation quality of highlighted buildings, specifically including: classifying and extracting the multi-spectral point cloud segmentation data of highlighted buildings in the third point cloud data acquisition area to obtain the reflectivity of the surface materials of highlighted buildings in the third point cloud data acquisition area; the reflectivity of the surface materials of highlighted buildings includes the maximum value of the reflectivity of the surface materials of highlighted buildings and the minimum value of the reflectivity of the surface materials of highlighted buildings; collect the maximum value of the night ambient light and the minimum value of the night ambient light in the third point cloud data acquisition area through a lux meter; analyze to obtain the noise correction value for the multi-spectral point cloud segmentation quality of highlighted buildings in the third point cloud data acquisition area.

[0116] In this embodiment, spectral library matching: match the collected spectral data with a spectral library of known materials to obtain the maximum value of the reflectivity of the surface materials of highlighted buildings and the minimum value of the reflectivity of the surface materials of highlighted buildings.

[0117] The noise correction value for the multi-spectral point cloud segmentation quality of highlighted buildings is used to describe the negative correction degree level of highlighted buildings affected by the multi-spectral point cloud acquisition quality.

[0118] Number the third point cloud data acquisition area, indicating the number of the third point cloud data acquisition area, indicating the total number of the third point cloud data acquisition areas.

[0119] indicating the noise correction value for the multi-spectral point cloud segmentation quality of highlighted buildings in the

[0120] ;

[0121] Extract predefined non-natural spectral component data from the multi-spectral image database of highlighted buildings;

[0122] indicating the maximum value of the reflectivity of the surface materials of highlighted buildings corresponding to the th point cloud data detection time period in the

[0123] indicating the minimum value of the reflectivity of the surface materials of highlighted buildings corresponding to the th point cloud data detection time period in the

[0124] indicating the maximum value of the reflectivity of the surface materials of highlighted buildings corresponding to the The standard value of the reflectivity of the surface material of highlighted buildings for a point cloud data detection time period. The standard value of the reflectivity of the surface material of highlighted buildings is directly obtained from the multi-spectral image database of highlighted buildings.

[0125] Surface material of the object under test: Different surface materials will reflect or absorb light of different wavelengths, thus affecting the quality of point cloud data. For example, if the reflectivities of different building surface materials vary too much, it will cause the previous contrast evaluation results to be too large.

[0126] Indicates the th corresponding maximum value of night ambient light for the th point cloud data detection time period in the

[0127] Indicates the th corresponding minimum value of night ambient light for the th point cloud data detection time period in the

[0128] Indicates the th corresponding standard value of night ambient light for the th point cloud data detection time period in the third point cloud data acquisition area. The standard value of night ambient light is directly obtained from the multi-spectral image database of highlighted buildings.

[0129] To measure the light intensity of artificial light sources, a lux meter is usually used. The higher the light intensity, the greater the possible impact on point cloud data. Artificial light sources around buildings (such as street lights, billboards, etc.) may cause interference (increase background noise). Spectral interference: Additional lights may introduce unnatural spectral components, interfering with the capture of the natural spectral characteristics of the building surface by the multi-spectral camera.

[0130] Indicates the noise error factor corresponding to the lidar used for acquisition, with a value range of (0, 1), representing the degree of influence of the corresponding noise error inherent in the lidar on the noise correction value for the multi-spectral point cloud segmentation quality of highlighted buildings, and is directly obtained from the multi-spectral image database of highlighted buildings through a pre-set mapping relationship.

[0131] Indicates the th in the The laser wavelength of a point cloud data detection time period. The wavelength affects the penetration ability of the laser and the reflectivity of different materials. Lasers with longer wavelengths have stronger penetration power, but may have lower resolution and are more susceptible to atmospheric scattering. Lasers with shorter wavelengths have high resolution, but weak penetration power and are easily absorbed and scattered by particulate matter such as water vapor and dust.

[0132] Indicates the th laser wavelength standard value of the th point cloud data detection time period of the first point cloud data acquisition area. The laser wavelength standard value is directly obtained from the high-light building multi-spectral image database.

[0133] Indicates the th laser divergence angle of the th point cloud data detection time period of the first point cloud data acquisition area. The laser divergence angle determines the focusing degree of the laser beam and affects the field of view angle of the lidar and the accuracy of the point cloud. A larger laser divergence angle will result in a decrease in the accuracy of the point cloud because the reflected signal comes from a larger area. Although a too small laser divergence angle can improve the accuracy, it will limit the detection range and may require a more complex scanning mechanism to cover a larger area.

[0134] Indicates the th laser divergence angle standard value of the th point cloud data detection time period of the first point cloud data acquisition area. The laser divergence angle standard value is directly obtained from the high-light building multi-spectral image database.

[0135] Furthermore, the specific process of comprehensively analyzing to obtain the comprehensive value of the high-light building multi-spectral point cloud segmentation quality is as follows: conduct a first evaluation and analysis on the high-light building multi-spectral point cloud segmentation data of the third point cloud data acquisition area to obtain the basic value of the fluctuation of the high-light building multi-spectral point cloud segmentation quality in the third point cloud data acquisition area; obtain the noise correction value of the high-light building multi-spectral point cloud segmentation quality in the third point cloud data acquisition area; comprehensively analyze the basic value of the fluctuation of the high-light building multi-spectral point cloud segmentation quality and the noise correction value of the high-light building multi-spectral point cloud segmentation quality in the third point cloud data acquisition area to obtain the comprehensive value of the high-light building multi-spectral point cloud segmentation quality.

[0136] In this embodiment, the comprehensive value of the high-light building multi-spectral point cloud segmentation quality is used to describe the negative comprehensive degree level of the influence of the high-light building on the multi-spectral point cloud acquisition quality.

[0137] Number the third point cloud data acquisition area, Indicates the number of the third point cloud data acquisition area, Indicates the total number of the numbers of the third point cloud data acquisition area.

[0138] Represents the comprehensive value of the segmentation quality of the highlighted building multispectral point cloud for the th third point cloud data acquisition area.

[0139] ;

[0140] Represents the basic value of the fluctuation of the segmentation quality of the highlighted building multispectral point cloud for the th third point cloud data acquisition area.

[0141] Represents the noise correction value of the segmentation quality of the highlighted building multispectral point cloud for the th third point cloud data acquisition area.

[0142] Represents the correction factor of the lidar dark current for the comprehensive value of the segmentation quality of the highlighted building multispectral point cloud, with a value range of (0, 1).

[0143] Under lightless conditions (e.g., placing the lidar in a completely light-shielded box or covering the lens with the camera's lid), a series of images are taken. These images will only contain the dark current noise generated by the lidar itself.

[0144] To improve the accuracy of calibration, multiple dark current images are taken.

[0145] Add all the dark current point cloud images and then divide by the number of images to obtain the average value of the dark current.

[0146] The correction factor of the lidar dark current for the comprehensive value of the segmentation quality of the highlighted building multispectral point cloud is directly obtained from the highlighted building multispectral image database through a pre-set mapping relationship.

[0147] For example, construct a mapping set of the lidar dark current and its corresponding correction factor of the lidar dark current for the comprehensive value of the segmentation quality of the highlighted building multispectral point cloud, and input the average value of the lidar dark current into the mapping set to obtain the weight factor of the correction factor of the lidar dark current for the comprehensive value of the segmentation quality of the highlighted building multispectral point cloud, where the mapping relationship is a one-to-one or many-to-one relationship.

[0148] Further, perform third point cloud data management processing according to the third comparison analysis result, specifically including: if the comprehensive value of the multi-spectral point cloud segmentation quality of the highlighted building is less than the comprehensive threshold of the multi-spectral point cloud segmentation quality of the highlighted building, no adjustment is made; if the comprehensive value of the multi-spectral point cloud segmentation quality of the highlighted building is greater than or equal to the comprehensive threshold of the multi-spectral point cloud segmentation quality of the highlighted building, then record the difference between the comprehensive value of the multi-spectral point cloud segmentation quality of the highlighted building and the comprehensive threshold of the multi-spectral point cloud segmentation quality of the highlighted building as the difference in the multi-spectral point cloud segmentation quality of the highlighted building; if the difference in the multi-spectral point cloud segmentation quality of the highlighted building is less than the difference threshold of the multi-spectral point cloud segmentation quality of the highlighted building, perform density filtering processing on the multi-spectral point cloud segmentation data of the highlighted building in the corresponding third point cloud data acquisition area; if the difference in the multi-spectral point cloud segmentation quality of the highlighted building is greater than or equal to the difference threshold of the multi-spectral point cloud segmentation quality of the highlighted building, perform bilateral filtering processing on the multi-spectral point cloud segmentation data of the highlighted building in the corresponding third point cloud data acquisition area.

[0149] In this embodiment, density-based filtering: In the shadow area, the point cloud density may be low. Use density-based filtering methods to identify and remove isolated points or outliers. For example, bilateral filtering combines spatial distance and intensity similarity to remove noise points while preserving edge information.

[0150] Bilateral filtering combines spatial distance and luminance similarity to remove outliers while preserving edge information.

[0151] Further, performing third point cloud data management processing according to the third comparison analysis result also includes: using the position positioning system built into the drone to collect data again according to the third point cloud data acquisition area and making a loop judgment until the comprehensive value of the multi-spectral point cloud segmentation quality of the highlighted building in the loop judgment is less than the comprehensive threshold of the multi-spectral point cloud segmentation quality of the highlighted building and the number of loop judgments is less than the loop judgment threshold; if the number of loop judgments is greater than or equal to the loop judgment threshold, notify relevant personnel of the corresponding third point cloud data acquisition area.

[0152] In this embodiment, in this embodiment, density-based filtering: In the shadow area, the point cloud density may be low. Use density-based filtering methods to identify and remove isolated points or outliers. For example, bilateral filtering combines spatial distance and intensity similarity to remove noise points while preserving edge information. Bilateral filtering combines spatial distance and luminance similarity to remove outliers while preserving edge information.

[0153] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0154] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0155] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0156] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0157] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0158] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. A method for managing high - light building point cloud data based on multi - spectral images, characterized in that, It includes the following steps: Use a drone to collect predefined spectral images of highlighted buildings, obtain the original multispectral image data and original lidar data of the highlighted buildings, and perform preprocessing to obtain the multispectral point cloud fusion data of the highlighted buildings; Segment the multispectral point cloud fusion data of the highlighted buildings according to the predefined fusion data size to obtain the segmented multispectral point cloud data of the highlighted buildings. Conduct a first comparative analysis on the segmented multispectral point cloud data of the highlighted buildings, and perform a first point cloud data management process based on the results of the first comparative analysis; Specifically, if the dispersion degree and contrast of the segmented multispectral point cloud data of the highlighted buildings are respectively less than the dispersion degree threshold and the contrast threshold, mark the corresponding segmented area as the first point cloud data acquisition area; Perform a first evaluation and analysis on the multi-spectral point cloud segmentation data of highlighted buildings to obtain the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of highlighted buildings. Indicates the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of highlighted buildings in the first cloud data acquisition area. ； and respectively represent the number and the total number of the point cloud data detection time periods; represents the natural constant; 、 and respectively represent the maximum value, the minimum value and the standard value of the highlight building reflectivity in the -th point cloud data detection time period of the -th first point cloud data acquisition area; 、 and respectively represent the maximum value, the minimum value and the standard value of the highlight building contrast in the -th point cloud data detection time period of the -th first point cloud data acquisition area; represents the highlight building radiance in the -th point cloud data detection time period of the -th first point cloud data acquisition area; represents the standard value of the highlight building radiance of the -th first point cloud data acquisition area; represents the weight factor of the difference between the maximum reflectivity and the minimum reflectivity of the highlighted building with respect to the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of the highlighted building; represents the weight factor of the difference between the maximum contrast and the minimum contrast of the highlighted building with respect to the basic value of the quality fluctuation of the multi-spectral point cloud segmentation of the highlighted building; represents the sensor resolution error factor; and respectively represent the atmospheric transmittance and the standard value of atmospheric transmittance in the -th point cloud data detection time period of the -th first point cloud data acquisition area; Conduct a second comparative analysis on the basic value of the segmentation quality fluctuation of the multispectral point cloud of the highlighted buildings, and perform a second point cloud data management process based on the results of the second comparative analysis; among them, if the basic value of the segmentation quality fluctuation of the multispectral point cloud of the highlighted buildings is less than the segmentation quality fluctuation threshold, mark the first point cloud data acquisition area as the third point cloud data acquisition area; Conduct a second evaluation analysis on the segmented multispectral point cloud data of the highlighted buildings in the third point cloud data acquisition area to obtain the segmentation quality noise correction value of the multispectral point cloud of the highlighted buildings; Comprehensively analyze the basic value of the segmentation quality fluctuation and the segmentation quality noise correction value of the multispectral point cloud of the highlighted buildings to obtain the comprehensive segmentation quality value of the multispectral point cloud of the highlighted buildings. Through a third comparative analysis based on the comprehensive segmentation quality value of the multispectral point cloud of the highlighted buildings, perform a third point cloud data management process based on the results of the third comparative analysis.

2. The method for managing highlighted building point cloud data based on multi-spectral images according to claim 1, wherein, The specific process of obtaining the multispectral point cloud fusion data of the highlighted buildings is as follows: Import the original multispectral image data of the highlighted buildings collected by the drone into the predefined spectral data processing software, and perform radiometric correction, geometric correction, and atmospheric correction on the original multispectral image data of the highlighted buildings through the predefined data processing software to obtain the corrected multispectral image data of the highlighted buildings; Import the original lidar data of the highlighted buildings collected by the drone into the predefined point cloud data processing software, and convert the original lidar data of the highlighted buildings into point cloud data of the highlighted buildings and remove abnormal points through the predefined point cloud data processing software to obtain the corrected point cloud data of the highlighted buildings; Perform position data annotation on the corresponding corrected multispectral image data and corrected point cloud data of the highlighted buildings according to the position positioning system built in the drone; Perform data fusion on the corresponding corrected multispectral image data and corresponding corrected point cloud data of the highlighted buildings according to the same position data annotation information to obtain the multispectral point cloud fusion data of the highlighted buildings.

3. The method for managing highlighted building point cloud data based on multi-spectral images according to claim 1, wherein, The first comparative analysis on the segmented multispectral point cloud data of the highlighted buildings specifically includes: Process different segmented multispectral point cloud data of the highlighted buildings through the predefined contrast software to obtain the dispersion degree of different segmented multispectral point cloud data of the highlighted buildings; Process the multispectral point cloud segmentation data of different highlighted buildings through predefined contrast software to obtain the contrast of the multispectral point cloud segmentation data of different highlighted buildings.

4. The method for managing highlighted building point cloud data based on multi-spectral images according to claim 1, wherein, Perform the first point cloud data management process according to the first comparative analysis result. The specific process is as follows: If the degree of dispersion of the multispectral point cloud segmentation data of the highlighted building is greater than or equal to the threshold of the degree of dispersion of the multispectral point cloud segmentation data of the highlighted building, mark the corresponding segmentation area as the second point cloud data acquisition area; If the contrast of the multispectral point cloud segmentation data of the highlighted building is greater than or equal to the threshold of the contrast of the multispectral point cloud segmentation data of the highlighted building, mark the corresponding segmentation area as the second point cloud data acquisition area; Obtain the position points corresponding to the second point cloud data acquisition area through the built-in position positioning tool of the drone. The drone flies to the corresponding position points to collect data again and make a loop judgment until the degree of dispersion of the multispectral point cloud segmentation data of the highlighted building in the loop judgment is less than the threshold of the degree of dispersion of the multispectral point cloud segmentation data of the highlighted building, the contrast of the multispectral point cloud segmentation data of the highlighted building is less than the threshold of the contrast of the multispectral point cloud segmentation data of the highlighted building, and the number of loop judgments is less than the loop judgment threshold; If the number of loop judgments is greater than or equal to the loop judgment threshold, notify the relevant personnel of the corresponding second point cloud data acquisition area.

5. The method for managing high - light building point cloud data based on multi - spectral images according to claim 1, wherein, Perform the second point cloud data management process according to the second comparative analysis result. The specific process is as follows: If the basic value of the segmentation quality fluctuation of the multispectral point cloud of the highlighted building is greater than or equal to the threshold of the segmentation quality fluctuation of the multispectral point cloud of the highlighted building, the drone reaches the first point cloud data acquisition area through the built-in position positioning system, opens the telescopic light shield and extends the exposure time to perform predefined spectral image acquisition, and makes a loop judgment until the basic value of the segmentation quality fluctuation of the multispectral point cloud of the highlighted building in the loop judgment is less than the threshold of the segmentation quality fluctuation of the multispectral point cloud of the highlighted building and the number of loop judgments is less than the loop judgment threshold; If the number of loop judgments is greater than or equal to the loop judgment threshold, notify the relevant personnel of the corresponding first point cloud data acquisition area.

6. The method for managing highlighted building point cloud data based on multi-spectral images according to claim 1, wherein The specific steps to obtain the noise correction value of the multispectral point cloud segmentation quality of the highlighted building include: Classify and extract the multispectral point cloud segmentation data of the highlighted building in the third point cloud data acquisition area to obtain the reflectivity of the surface material of the highlighted building in the third point cloud data acquisition area; The reflectivity of the surface material of the highlighted building includes the maximum value of the reflectivity of the surface material of the highlighted building and the minimum value of the reflectivity of the surface material of the highlighted building; Collect the maximum value of the night ambient light and the minimum value of the night ambient light in the third point cloud data acquisition area through a lux meter; Analyze to obtain the noise correction value of the multispectral point cloud segmentation quality of the highlighted building in the third point cloud data acquisition area.

7. The method for managing high-light building point cloud data based on multi-spectral images according to claim 1, wherein The specific process of comprehensively analyzing and obtaining the comprehensive value of the multispectral point cloud segmentation quality of the highlighted building is as follows: Perform the first evaluation and analysis on the multispectral point cloud segmentation data of the highlighted building in the third point cloud data acquisition area to obtain the basic value of the segmentation quality fluctuation of the multispectral point cloud of the highlighted building in the third point cloud data acquisition area; Obtain the high - light building multispectral point cloud segmentation quality noise correction value for the third point cloud data acquisition area; Comprehensively analyze the high - light building multispectral point cloud segmentation quality fluctuation base value and the high - light building multispectral point cloud segmentation quality noise correction value for the third point cloud data acquisition area to obtain the high - light building multispectral point cloud segmentation quality comprehensive value.

8. The method for managing high - light building point cloud data based on multi - spectral images according to claim 1, wherein The third point cloud data management process according to the third comparative analysis result specifically includes: If the high - light building multispectral point cloud segmentation quality comprehensive value is less than the high - light building multispectral point cloud segmentation quality comprehensive threshold, do not adjust; If the high - light building multispectral point cloud segmentation quality comprehensive value is greater than or equal to the high - light building multispectral point cloud segmentation quality comprehensive threshold, record the difference between the high - light building multispectral point cloud segmentation quality comprehensive value and the high - light building multispectral point cloud segmentation quality comprehensive threshold as the high - light building multispectral point cloud segmentation quality difference; If the high - light building multispectral point cloud segmentation quality difference is less than the high - light building multispectral point cloud segmentation quality difference threshold, perform density filtering on the high - light building multispectral point cloud segmentation data for the corresponding third point cloud data acquisition area; If the high - light building multispectral point cloud segmentation quality difference is greater than or equal to the high - light building multispectral point cloud segmentation quality difference threshold, perform bilateral filtering on the high - light building multispectral point cloud segmentation data for the corresponding third point cloud data acquisition area.

9. The method for managing highlighted building point cloud data based on multi-spectral images according to claim 1, wherein The third point cloud data management process according to the third comparative analysis result also includes: Use the position - positioning system built into the drone to re - collect data according to the third point cloud data acquisition area and make a loop judgment until the high - light building multispectral point cloud segmentation quality comprehensive value in the loop judgment is less than the high - light building multispectral point cloud segmentation quality comprehensive threshold and the loop judgment times are less than the loop judgment threshold; If the loop judgment times are greater than or equal to the loop judgment threshold, notify the relevant personnel of the corresponding third point cloud data acquisition area.

Images