A method and system for surveying an area along a railway line based on a drone

Abstract

The embodiment of the application provides a railway line surrounding area surveying and mapping method and system based on a UAV, and belongs to the technical field of area surveying and mapping. The method comprises the following steps: performing coordinate registration processing on laser point cloud data collected by a UAV and a railway red line vector diagram to obtain standard point cloud data and a red line reference boundary in a unified coordinate system; based on the standard point cloud data and the red line reference boundary, edge point sets of an actual occupied area outside the red line are extracted, and a closed boundary contour is fitted; based on the fitted boundary contour, unified plane projection and subdivision processing are performed to generate a two-dimensional measurement grid for area determination; based on the two-dimensional measurement grid, the areas of units are accumulated, and the total area of the extended area outside the red line and the corresponding boundary coordinates are output. The scheme of the application realizes high-precision and full-process area surveying and mapping of non-standard occupied areas along a railway line, and improves the objectivity of boundary judgment and the stability of area extraction results.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of area mapping, in particular to a railway line surrounding area mapping method based on a UAV and a railway line surrounding area mapping system based on a UAV. BACKGROUND

[0002] Railway line land management has long relied on red line boundaries as the spatial basis for land use rights, however, in actual operation and construction processes, there are often situations such as road toe expansion, spoil stacking, and slope vegetation spreading outside the red line range, forming an "extended area outside the red line". These areas, although not within the legal boundaries, are highly coupled with railway operation in space, and the accurate measurement of their occupied range is directly related to land compliance evaluation, relocation compensation judgment, and illegal building supervision and other management activities.

[0003] Currently, the measurement of such areas mostly uses manual field reconnaissance or visual interpretation methods based on remote sensing images, which have problems such as difficult closure of the measurement area, boundary judgment relying on subjective experience, and poor area calculation accuracy. In actual scenarios, due to the spatial characteristics of the extended area outside the red line, such as irregularity and lack of clear structure boundaries, the transition zone at the edge of the measurement area often exists in a natural state, such as grassy slopes, gravel layers, or spoil piles, making it difficult for traditional methods to determine accurate boundaries based on image texture or GPS traces. In addition, when the measurement area does not form a natural closed structure, there is a lack of suitable closed fitting and projection measurement mechanisms, often causing boundary instability and error accumulation in area calculation.

[0004] Therefore, in view of the difficulties in boundary identification and area measurement in the extended area outside the red line, it is urgent to establish a spatial mapping mechanism with boundary adaptability and high-precision area extraction capability to improve the measurement efficiency and judgment reliability of non-standard occupied areas along the railway line. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide a railway line surrounding area mapping method and system based on a UAV to at least solve the problems of difficult boundary identification, insufficient closure of the measurement area, and unstable accuracy of the area measurement result in the extended area outside the red line in the prior art.

[0006] To achieve the above object, the present application provides a railway along the line of the surrounding area mapping method based on unmanned aerial vehicle, the method comprises: the laser point cloud data collected by unmanned aerial vehicle and railway red line vector diagram is carried out coordinate registration processing, obtains the standard point cloud data and red line reference boundary under the unified coordinate system; based on the standard point cloud data and red line reference boundary, the edge point set of the actual occupied area outside the red line is extracted, and the closed boundary contour is fitted; based on the fitted boundary contour, unified plane projection and section processing are carried out, and two-dimensional measurement grid for area determination is generated; based on the two-dimensional measurement grid, the unit area is accumulated and the total area of the extended area outside the red line and the corresponding boundary coordinates are output.

[0007] Optionally, the laser point cloud data collected by unmanned aerial vehicle and railway red line vector diagram is carried out coordinate registration processing, obtains the standard point cloud data and red line reference boundary under the unified coordinate system, comprising:

[0008] The time synchronization position information output by the global positioning system carried by the unmanned aerial vehicle and the flight attitude data output by the inertial navigation system are acquired;

[0009] The space trajectory model of the laser point cloud is constructed based on the time synchronization position information and the flight attitude data, so that the original coordinates of each measurement point in the laser point cloud are compensated and calculated based on the space trajectory model;

[0010] The compensated laser point cloud coordinates are projected and converted with the geographic reference coordinate system used by the railway red line vector diagram, and the standard point cloud data and the red line reference boundary under the unified coordinate system are generated.

[0011] Optionally, based on the standard point cloud data and the red line reference boundary, the edge point set of the actual occupied area outside the red line is extracted, comprising:

[0012] The elevation difference value of each measurement point relative to its neighborhood point is determined based on the standard point cloud data, and the point cloud elevation difference gradient graph is constructed;

[0013] Based on the point cloud elevation difference gradient graph, the position with the elevation difference value greater than the preset difference threshold is taken as the edge candidate point set;

[0014] The edge candidate point set and the red line reference boundary are judged in space relationship, and the measurement point located outside the red line and the elevation difference value greater than the preset difference threshold relative to its neighborhood point are screened out to form the edge point set.

[0015] Optionally, the fitting rule of the closed boundary contour is:

[0016] The edge point set is sorted according to the curvature perception in two-dimensional space coordinates, and the edge path fitting is carried out based on the smooth closed interpolation algorithm with minimum curvature change to form the closed boundary contour; wherein,

[0017] If the sorted edge point set does not form a closed boundary contour, a shortest connection segment between the first and the last edge point is introduced to complete the edge path during the fitting process to form a closed boundary contour.

[0018] Optionally, the rule for performing the unified planar projection is:

[0019] A major axis direction of the closed boundary contour obtained through the fitting is calculated, and a local measurement reference plane is constructed based on the major axis direction; wherein,

[0020] The measurement reference plane is established as a two-dimensional planar rectangular coordinate system with a geometric center point of the boundary contour as an origin and the major axis direction as an X-axis direction;

[0021] All boundary point coordinates in the closed boundary contour are transformed to the measurement reference plane to obtain a projection contour of the boundary contour under the corresponding two-dimensional coordinate system;

[0022] A minimum circumscribed rectangular region containing all the projection points is calculated based on the boundary point coordinate set in the projection contour, and the circumscribed rectangular region is taken as a spatial boundary constraint for the measurement grid division, used to limit the spatial range of the measurement region.

[0023] Optionally, the rule for generating the two-dimensional measurement grid is:

[0024] Within the minimum circumscribed rectangular range, a Delaunay triangulation algorithm is performed with the projection contour boundary as a mandatory constraint boundary to generate a two-dimensional measurement grid cell covering the inside of the closed boundary; wherein,

[0025] A grid quality factor is introduced for each division cell in the Delaunay triangulation algorithm for quality control to eliminate degenerate cells that do not meet the preset minimum angle requirement.

[0026] Optionally, based on the two-dimensional measurement grid, the areas of all cells are accumulated and the total area and corresponding boundary coordinates of the redline outer expansion region are output, including:

[0027] For each triangular cell in the two-dimensional measurement grid, the corresponding vertex coordinates are obtained and the cell area is calculated according to the planar geometric rules to obtain the cell area of the corresponding measurement grid;

[0028] The cell areas of all measurement grids are sequentially accumulated to obtain the total area; wherein,

[0029] Before the total area is obtained by sequentially accumulating the cell areas of all measurement grids, the cell area calculation results of each measurement grid are spatially labeled and associated with the closed boundary contour for verification to ensure that all area results fall within the boundary range.

[0030] Optionally, the method further comprises performing measurement result output, comprising:

[0031] combining the measured total area with the corresponding boundary coordinates into a planar area object, and exporting in GeoJSON or Shapefile format;

[0032] generating a metadata file related to the present measurement, the metadata file comprising acquisition time, point cloud density, attitude compensation parameters and projection plane definition; wherein,

[0033] the planar area object and the metadata file together constitute a structured survey output result output.

[0034] The second aspect of the present application provides a railway line along the surrounding area area surveying system based on unmanned aerial vehicle, the system comprises: acquisition unit, for performing coordinate registration processing on the laser point cloud data collected by unmanned aerial vehicle and railway red line vector map, obtaining standard point cloud data and red line reference boundary in unified coordinate system; fitting unit, for extracting edge point set of actual occupied area outside the red line based on the standard point cloud data and the red line reference boundary, and fitting to obtain a closed boundary contour; processing unit, for performing unified plane projection and subdivision processing based on the fitted boundary contour, generating a two-dimensional measurement grid for area determination; output unit, for accumulating the area of each unit based on the two-dimensional measurement grid and outputting the total area and corresponding boundary coordinates of the extended area outside the red line.

[0035] In another aspect, the present application provides a computer readable storage medium, which stores instructions that, when executed on a computer, cause the computer to perform the above-mentioned railway line along the surrounding area area surveying method based on unmanned aerial vehicle.

[0036] Through the above technical solution, the present application establishes a unified coordinate system based on coordinate registration of laser point cloud data and railway red line vector map, effectively eliminating the spatial offset problem caused by inconsistent data sources; based on the unified spatial reference, the edge point set of the extended area outside the red line is extracted, and a closed boundary contour is generated by fitting, realizing automatic recognition and closed control of the boundary of the natural transition area; further, the closed contour is projected and subdivided into a structured two-dimensional measurement grid, ensuring the integrity and integrability of the area calculation range; finally, through the accumulation of each grid unit area, the total area and boundary information of the extended area outside the red line are output, realizing high-precision, full-process area surveying of non-standard occupied areas along the railway line, and improving the objectivity of boundary judgment and the stability of area extraction results.

[0037] Other features and advantages of the present application will be described in detail in the following specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0038] The accompanying drawings are included to provide a further understanding of embodiments of the application, and are incorporated in and constitute a part of this specification, illustrate embodiments of the application, and together with the description serve to explain embodiments of the application, but are not intended to limit the present application in any manner. In the drawings:

[0039] Figure 1 is a step flow chart of a railway line surrounding area mapping method based on a UAV provided by an embodiment of the present application;

[0040] Figure 2 is a schematic diagram of an edge point set fitting closed path forming process provided by an embodiment of the present application;

[0041] Figure 3 is a system structure diagram of a railway line surrounding area mapping system based on a UAV provided by an embodiment of the present application. DETAILED DESCRIPTION

[0042] The specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to illustrate and explain the present application, and are not intended to limit the present application.

[0043] Figure 1 is a step flow chart of a railway line surrounding area mapping method based on a UAV provided by an embodiment of the present application. As shown in Figure 1 , the present application provides a railway line surrounding area mapping method based on a UAV, which comprises the following steps:

[0044] Step S10: Perform coordinate registration processing on the laser point cloud data collected by the UAV and the railway red line vector map to obtain standard point cloud data and red line reference boundaries in a unified coordinate system.

[0045] Specifically, time-synchronized position information output by a global positioning system carried by the UAV and flight attitude data output by an inertial navigation system are obtained; a spatial trajectory model of the laser point cloud is constructed based on the time-synchronized position information and the flight attitude data, so as to perform attitude compensation and position calculation on the original coordinates of each measurement point in the laser point cloud based on the spatial trajectory model; the compensated laser point cloud coordinates are projected and converted and aligned with the geographic reference coordinate system used by the railway red line vector map to generate standard point cloud data and red line reference boundaries in a unified coordinate system.

[0046] In the embodiment of the present application, in the area mapping process of the expansion area outside the railway red line, in order to ensure the consistency and measurement accuracy of the spatial data, the laser point cloud data collected by the unmanned aerial vehicle and the railway red line vector map need to be coordinate registered to construct the mapping basic data under the unified spatial reference system. The processing flow mainly includes two parts: one is to compensate the attitude of the laser point cloud data and solve the position to form standard point cloud data; the second is to align the coordinates of the standard point cloud data and the geographic reference coordinate system relied on by the railway red line vector map, and finally realize the unification of the space reference, and lay a high-precision data foundation for subsequent boundary recognition and area calculation.

[0047] Specifically, first, in the laser point cloud collection stage, the time synchronization position information output by the global positioning system (GPS) carried by the unmanned aerial vehicle platform and the flight attitude data output by the inertial navigation system (INS) are obtained, including roll angle (Roll), pitch angle (Pitch) and yaw angle (Yaw). The GPS provides discrete space-time position points, and the INS provides high-frequency attitude change information. By time synchronizing the two, the complete spatial pose trajectory of the aircraft during laser scanning can be constructed.

[0048] After obtaining the above data, combined with the ranging angle, emission direction and echo intensity information recorded inside the laser radar, the original relative coordinates of each laser dot in the three-dimensional space are constructed. Based on the position provided by the GPS and the attitude angle provided by the INS, the relative coordinates are subjected to three-dimensional rigid body transformation to complete the attitude compensation and geographical position solution of each measurement point in the point cloud. This process is essentially to convert the relative ranging results in the airborne coordinate system to the absolute position representation in the geographic spatial reference system, and the output is a laser point set containing X, Y and Z coordinates, which is the point cloud data after attitude correction.

[0049] Subsequently, the compensated point cloud data is subjected to geographic projection transformation to convert its coordinate system to be consistent with the coordinate reference adopted by the railway red line vector map. Usually, the railway land data adopts Gauss-Kruger projection or WGS84 coordinate system, and according to the specific definition of the red line data, the corresponding projection parameters are selected to perform coordinate conversion operation to avoid spatial registration error caused by data misplacement in different coordinate systems. In this process, the projection zone number, central meridian, ellipsoid parameters and other key elements need to be strictly checked to ensure that the point cloud data and the vector boundary are aligned under the same geographic reference.

[0050] After the projection conversion is completed, the point cloud data is superimposed with the railway red line vector diagram, spatial coordinate alignment verification is performed, and it is confirmed that the position error of the two types of data in the boundary adjoining area is within the preset tolerance range. If there is a slight deviation, fine tuning can be performed based on the common control points or boundary coincidence degree, and finally the standard point cloud data and the red line reference boundary in the unified coordinate system are generated. The result is used as the basic input for subsequent boundary extraction, area subdivision, and projection calculation, and has the technical advantages of unified spatial reference, accurate attitude compensation, and traceable coordinate conversion.

[0051] The coordinate registration processing not only solves the problem of inconsistent coordinate systems between the laser point cloud and the railway vector diagram, but also effectively eliminates the point cloud spatial distortion caused by changes in flight attitude, providing clear structure and accurate positioning of the basic data input for boundary contour extraction and area measurement in the red line extension area, significantly improving the reliability of subsequent boundary identification and the spatial accuracy of measurement results.

[0052] In another possible implementation, for the problems of easy obstruction of GPS signals and inaccurate attitude compensation in complex terrain areas, a registration method based on joint inversion of laser point cloud and ground control points is used to replace the traditional method of completely relying on navigation units to construct a spatial trajectory model. Specifically, a number of ground control points are laid out in the survey area in advance, and their known three-dimensional coordinates are recorded in the reference coordinate system. During the execution of the laser scanning task, the system marks the echo recognition results of these control points in the laser point cloud in real time, and extracts the point cloud subset containing the features of the ground control points.

[0053] Subsequently, based on the spatial distribution characteristics of the control points and the positioning results in the actual point cloud, a rigid transformation model is used to perform coordinate inversion on the entire point cloud data set, automatically adjusting the original point cloud to the target geographic reference system, and realizing spatial calibration under attitude disturbance. Compared with the forward calculation method based on the flight trajectory, the reverse calibration method based on known control points is more suitable for environments with strong interference, unstable attitude, or short-term interruption of GNSS signals, improving the robustness of point cloud positioning. The point cloud data after transformation and the railway red line vector diagram complete boundary alignment in the same coordinate system, and the standard point cloud data and the red line reference boundary under the unified spatial reference are obtained, which are used for subsequent boundary contour extraction and area calculation.

[0054] Step S20: Based on the standard point cloud data and the red line reference boundary, the edge point set of the actual occupied area outside the red line is extracted, and a closed boundary contour is fitted.

[0055] Specifically, based on the standard point cloud data and the red line reference boundary, edge point sets of the actual occupied area outside the red line are extracted, including: determining the elevation difference of each measurement point relative to its neighborhood points based on the standard point cloud data, and constructing a point cloud elevation difference gradient map; based on the point cloud elevation difference gradient map, positions with an elevation difference greater than a preset difference threshold are taken as an edge candidate point set; the edge candidate point set and the red line reference boundary are subjected to spatial relationship judgment, and measurement points located outside the red line and having an elevation difference greater than the preset difference threshold relative to their neighborhood points are screened out to form an edge point set.

[0056] Further, the fitting rule of the closed boundary contour is: the edge point set is sorted according to curvature perception in two-dimensional space coordinates, and the edge path fitting is performed based on a smooth closed interpolation algorithm with minimum curvature change to form a closed boundary contour; wherein, if the sorted edge point set does not constitute a closed boundary contour, a shortest connection segment between the beginning and the end is introduced in the fitting process to complete the edge path fitting to form a closed boundary contour.

[0057] In the embodiment of the present application, after completing the unified coordinate registration of the standard point cloud data and the red line reference boundary, in order to further identify the actual occupied range of the railway red line expansion area, the edge point set of the area needs to be extracted from the standard point cloud data, and a closed boundary contour is fitted based on the edge point set, which is used for subsequent measurement grid subdivision and area calculation. This process needs to consider the terrain change characteristics and the red line constraint condition at the same time, so as to ensure that the identified boundary truly reflects the actual occupied contour, and has high geometric stability and closed integrity.

[0058] Specifically, the extraction of the edge point set is based on the standard point cloud data as the input, first, the neighborhood relationship of each point cloud measurement point is constructed, and the fixed search radius method or the k nearest neighbor method is usually used to determine the local neighborhood point set. For each measurement point, the elevation difference between the elevation of the measurement point in the Z direction and all neighborhood points is calculated, and the maximum elevation difference of the measurement point is taken as the local elevation difference response value of the measurement point. Further, in the whole point cloud range, the elevation difference response values of all measurement points are summarized to construct a point cloud elevation difference gradient map, forming a spatial elevation difference distribution data set related to the terrain mutation. The elevation difference gradient map serves as the basis for boundary determination, which can reveal the fluctuation jump area of the local terrain, and is convenient for identifying the natural or man-made occupied edge zone such as the geomorphic boundary, the accumulation contour and the vegetation boundary.

[0059] After obtaining the height difference gradient map, preliminary screening is performed based on a set difference threshold to identify measurement points with a height difference value greater than the threshold, and the measurement points are taken as an initial edge candidate point set. The difference threshold should be adaptively adjusted according to the types of field objects, point cloud density and scanning accuracy. In general, the difference threshold is taken as 3 to 5 times the standard deviation of point cloud noise, which can effectively eliminate the false judgment interference caused by local micro relief. To avoid misjudgment of natural relief areas inside the red line as boundary areas, spatial position filtering is further performed in combination with the red line reference boundary. That is, for each point in the edge candidate point set obtained through preliminary screening, it is determined whether the point is located outside the red line reference boundary. If the point satisfies the spatial relationship constraint and the maximum height difference value of the point is still higher than the preset threshold, the point is finally retained as an edge point and added to the edge point set.

[0060] It is worth noting that the "located outside the red line" is not a simple judgment of the direction of the point outside the boundary line, but a strict geometric relationship judgment in the form of point-in-polygon judgment or construction of a spatial buffer zone according to the vector polygon structure of the red line boundary, to avoid spatial relationship misjudgment caused by complex boundary line morphology or measurement error. The finally formed edge point set should have the following attribute characteristics: the spatial position is concentrated in the external region of the red line; the local topographic feature is characterized by obvious height difference mutation; and the spatial distribution is in a continuous band shape along the edge of the actual occupied area.

[0061] After obtaining the edge point set, to ensure the effectiveness and integrability of subsequent area measurement, the edge point set needs to be fitted into a continuous closed boundary contour. The fitting rule of the boundary contour is as follows: first, the edge point set is sorted according to its two-dimensional spatial coordinates. The sorting process combines the overall geometric distribution of the point set, and usually uses a perception sorting method based on the direction of curvature. Specifically, a spatially outermost edge point is selected as the starting point, the direction of the line connecting the starting point and its adjacent points is calculated, and the direction is taken as the starting point to guide the sorting of the entire point set along the path with the minimum curvature change, so as to restore the actual boundary as much as possible.

[0062] After completing the sorting of the point set, a smooth closed interpolation algorithm is performed based on the sequence to construct a continuous boundary path. Common interpolation methods include spline curve interpolation, B-spline fitting or flexible fitting method based on local weighted regression. To avoid sharp corners or contour breaks in the point sparse area, a minimum curvature change constraint is introduced in the fitting process to smooth the angle between adjacent segments of the interpolation path, so as to ensure that the boundary contour as a whole presents a smooth and closed state. In the case of uneven edge point density or local discontinuity of the contour, the method can automatically perform a relief transition between paths to improve the integrity of the fitted contour.

[0063] When the fitting path fails to form a closed structure naturally, for example, there is a spatial distance between the starting point and the ending point that is greater than the set closure tolerance, a contour patch mechanism is introduced. In this mechanism, the Euclidean distance between the first and last points in the order is calculated, and a patch is added to the boundary contour as part of the fitting path. The patch can be connected by a linear connection, a circular arc connection, or interpolation according to the local curvature trend. The specific way is selected according to the difference between the first and last direction vectors and the overall bending trend of the point set. The introduction of the patch ensures the closure of the topological structure of the fitting path, and avoids the problem of grid fragmentation or area loss in the subsequent subdivision process due to the non-closure of the contour.

[0064] The finally generated closed boundary contour is not only continuous and closed in geometric structure, but also strictly located outside the red line reference boundary in space, and the corresponding edge points all have the characteristics of height difference mutation, which can accurately describe the outward expansion boundary form of the actual occupied area outside the red line. The closed contour will serve as the spatial input boundary for the subsequent projection subdivision and measurement grid generation, playing a key role in area calculation and integral region control, effectively improving the boundary consistency of the area result and the geometric controllability of the measurement area.

[0065] In one possible implementation, as Figure 2 , Figure 2 (a) shows the boundary contour fitting result in an ideal case, where the edge point set is sorted by curvature perception and a continuous path is formed by fitting a smooth curve. The fitting path is naturally closed, and the first and last points are precisely connected in space. The final closed boundary contour is generated.

[0066] Figure 2 (b) shows a case where the fitting path is not naturally closed, i.e., after fitting the edge point set, the resulting path fails to close at the beginning and end, leaving a certain spatial gap. To form a closed boundary structure, a shortest connecting edge segment is introduced at the beginning and end of the fitting process to connect the first and last points of the path, forming a closed region. In the illustration, the connecting edge segment is represented by a dashed line to distinguish it from the original fitting curve. It should be noted that the connecting edge segment is not limited to a straight line segment in the absolute sense, and its form can be adjusted according to the actual spatial distribution between the first and last points, the overall trend of the boundary, and the fitting strategy. For example, in the case of curvature constraints, the introduced connecting edge segment can be a smooth curve, but in all cases, it should satisfy the principle of "the shortest feasible path between the first and last points" to ensure that the contour structure is closed in geometry and topology, and to avoid problems such as boundary rupture or closure failure in the subsequent measurement area subdivision process.

[0067] Through the above edge point extraction and contour fitting process, the problems that the traditional image interpretation mode is difficult to identify the boundary transition zone and the boundary of the natural occupied area is blurred are solved, an automatic boundary identification mechanism based on height difference characteristics and spatial constraints is constructed, a strong geometric support foundation for the accurate measurement of the railway red line extension area is provided, and the objectivity, reproducibility and applicability of the boundary extraction in the red line extension area surveying and mapping task are effectively improved.

[0068] Step S30: based on the fitted boundary contour, performing unified plane projection and subdivision processing to generate a two-dimensional measurement grid for area determination.

[0069] Specifically, based on the fitted boundary contour, performing unified plane projection and subdivision processing includes: calculating the principal axis direction of the closed boundary contour based on the fitted boundary contour, and constructing a local measurement reference plane based on the principal axis direction; wherein the measurement reference plane establishes a two-dimensional plane rectangular coordinate system with the geometric center point of the boundary contour as the origin and the principal axis direction as the X-axis direction; the coordinates of all boundary points in the closed boundary contour are transformed to the measurement reference plane to obtain the projection contour of the boundary contour in the corresponding two-dimensional coordinate system; the minimum circumscribed rectangle region containing all the projection points is calculated based on the boundary point coordinate set in the projection contour, and the circumscribed rectangle region is taken as the spatial boundary constraint of the measurement grid subdivision, which is used to limit the spatial range of the measurement area.

[0070] Further, the generation rule of the two-dimensional measurement grid is: within the minimum circumscribed rectangle range, taking the projection contour boundary as the mandatory constraint boundary, performing the Delaunay triangulation algorithm to generate a two-dimensional measurement grid cell covering the inside of the closed boundary; wherein a grid quality factor is introduced for each subdivision cell in the Delaunay triangulation algorithm for quality control to eliminate the degenerate cells that do not meet the preset minimum angle requirement.

[0071] In the embodiment of the present application, after the identification of the edge point set and the smooth fitting of the boundary contour are completed, in order to realize the accurate measurement of the area of the red line extension area, the boundary contour in the three-dimensional space needs to be further projected to a unified two-dimensional measurement plane, and the grid subdivision processing is performed in the plane to generate a measurement grid with clear structure and geometric closure, so as to support the quantitative integral calculation of the area. This process not only involves the conversion and normalization processing of the coordinate system, but also needs to accurately close the boundary of the measurement area and generate high-quality grid cells through a suitable subdivision algorithm to ensure the stability of the subsequent area calculation and the repeatability of the measurement results.

[0072] Specifically, first, the principal axis direction of the closed boundary contour obtained by fitting is determined. The principal axis direction is the main reference axis describing the extension direction of the boundary contour in the two-dimensional plane, which is used to construct a local coordinate reference system to improve the clarity of the expression of the projected boundary shape. The principal axis direction can be calculated by the least square fitting ellipse principal axis method of the boundary point set, or by principal component analysis (PCA) of the covariance matrix of the boundary point set to obtain the first principal component direction as the principal axis direction vector. Taking the ellipse fitting method as an example, assuming that the two-dimensional coordinates of the boundary point set after spatial projection are (xi, yi), the long axis direction of the fitted ellipse, i.e., the principal axis direction of the boundary contour, is obtained by minimizing the sum of the square residuals of the boundary points to the edge of the ellipse.

[0073] After obtaining the principal axis direction, a local measurement reference plane is constructed. The reference plane takes the geometric center point of the boundary contour as the origin and the principal axis direction as the X-axis direction to construct a two-dimensional plane rectangular coordinate system. The geometric center point can be obtained by averaging the X and Y coordinates of all boundary points, which represents the center position of the region where the boundary is located. In order to make the coordinate system have good coordinate orthogonality, it is further necessary to calculate the angle between the principal axis direction and the global reference coordinate axis to construct a rotation transformation matrix, which maps all boundary point coordinates from the original global coordinate system to the local two-dimensional coordinate system, realizing the plane projection of the boundary points.

[0074] During the projection process, the following transformation is performed on each boundary point coordinate: first, the position vector of the point is translated to the local coordinate system with the geometric center point as the origin, and then the rotation matrix constructed according to the principal axis direction is used to linearly transform the vector to obtain the two-dimensional projection coordinates in the local coordinate system. The mathematical expression of the transformation is:

[0075] ;

[0076] where (x, y) is the original coordinate, (x c ,y c ) is the coordinate of the geometric center point, and R is the two-dimensional rotation matrix constructed based on the principal axis direction. Through the coordinate transformation, the coordinates of all boundary points in the two-dimensional measurement reference plane can be obtained, thereby forming a "projected contour".

[0077] After obtaining the projection contour, a minimum bounding rectangle covering the contour region needs to be further constructed to determine the boundary control range of the grid partition. The minimum bounding rectangle is the smallest area rectangle containing all the boundary points of the projection, and its boundary direction is aligned with the coordinate axes of the measurement plane, which is used to define the spatial encapsulation range of the subsequent partition operation. The calculation of the minimum bounding rectangle can be based on the set of boundary points to perform the rotating calipers algorithm or the convex hull envelope method, and the coordinates of the corner points are used to define the spatial boundary box of the measurement region. This boundary box limits the boundary region of the generated partition grid on the one hand, and also serves as the basic unit for measurement graphics visualization and data structure organization on the other hand.

[0078] After completing the measurement plane construction and projection contour envelope, the partitioning phase of the two-dimensional measurement grid is entered. The partitioning operation needs to be based on the principles of high conformality, integrability, and boundary constraint. The preferred algorithm is Delaunay triangulation. This algorithm ensures that the grid is non-overlapping and maximizes the minimum angle, and can generate a triangular grid with high geometric quality, which is beneficial for subsequent integration and graphic analysis. Before performing Delaunay partitioning, the projection contour is input as a boundary constraint, so that the partitioning process is only performed inside the closed boundary, and all triangular grid elements generated by partitioning are constrained within the closed boundary. For this purpose, the Constrained Delaunay Triangulation (CDT) strategy can be used to introduce boundary vertex chain constraints into the standard partitioning algorithm to ensure that the boundary is accurately transmitted to the partitioning structure.

[0079] During the partitioning process, a grid quality control constraint is applied to each triangular element. Typically, the minimum internal angle of each triangle is set to be no less than 20° or the maximum aspect ratio is set to be no more than a certain threshold, to avoid integration distortion or calculation instability caused by sharp angles or long strip shapes. Quality control can be achieved by performing local optimization operations (such as edge flipping and node smoothing) after initial partitioning, or by adjusting the partitioning density through pre-processing such as density control point placement before partitioning. If degenerate elements (such as triangles with extremely small area or extremely sharp angles) are generated during the partitioning process, a unit screening and removal operation should be performed after partitioning to remove grid elements that do not meet the quality factor, and re-partitioning is performed to complete the adjacent structure.

[0080] In addition, to ensure the closed integrity of the area calculation, connectivity analysis and boundary closure verification need to be performed on the final generated two-dimensional measurement grid structure. By traversing the spatial relationship between the grid boundary elements and the projection contour, it is confirmed that all grid boundaries strictly coincide with the closed contour, avoiding the occurrence of edge penetration, edge omission or disconnected regions during the partitioning process. If isolated grid segments or internal hole regions are found to be uncovered, a supplementary partitioning mechanism or local grid expansion operation can be introduced to complete the closure, ensuring the completeness of the measurement region topology.

[0081] The resulting two-dimensional measurement grid consists of a large number of high-quality triangular units with confined boundaries, and has the following technical advantages: First, all grid units completely cover the closed boundary of the extended area outside the red line, ensuring the consistency of the measurement area for area calculation; Second, all grid units meet geometric quality constraints, avoiding the accumulation of calculation errors; Third, the boundary contours are completely embedded in the grid structure in a structured manner, providing high traceability and user-friendly graphical visualization.

[0082] This processing not only establishes a complete geometric mapping mechanism from 3D boundary contours to 2D integral regions, but also provides a precise, closed, and structurally stable grid carrier for area measurement. It exhibits high adaptability and repeatability in automated mapping of large-scale railway land use areas outside the red line. Especially in scenarios with complex terrain, irregular land use areas, or discontinuous boundaries, the measurement grid constructed through unified projection and high-quality subdivision effectively avoids problems such as boundary distortion, projection skew, or area omissions inherent in traditional image-based or manual estimation methods. This enhances the technical reliability and automation level of identifying and extracting areas of non-planned regions in railway land use supervision.

[0083] Step S40: Based on the two-dimensional measurement grid, accumulate the area of ​​each unit and summarize and output the total area and corresponding boundary coordinates of the extended area outside the red line.

[0084] Specifically, for each triangular cell in the two-dimensional measurement grid, the corresponding vertex coordinates are obtained and the cell area is calculated according to the plane geometry rules to obtain the cell area of ​​the corresponding measurement grid; the cell areas of all measurement grids are sequentially summed to obtain the total area; before the process of sequentially summing the cell areas of all measurement grids to obtain the total area, the cell area calculation results of each measurement grid are spatially marked and correlated with the closed boundary contour to ensure that all area results fall within the boundary range.

[0085] In this embodiment of the invention, after the projection and subdivision of the two-dimensional measurement grid are completed, it is necessary to further calculate the actual occupied area of ​​the extended region outside the red line based on the generated measurement grid structure, and output the corresponding boundary information for visualization and data archiving. To achieve this goal, the area of ​​each triangular unit constituting the two-dimensional measurement grid must first be calculated, and then the area results of all units are accumulated one by one to finally obtain the complete total area value. At the same time, a spatial consistency verification mechanism must be introduced during the area calculation process to ensure that each grid unit included in the total area falls strictly within the previously fitted closed boundary contour, avoiding area deviations caused by boundary errors or subdivision redundancy.

[0086] Specifically, for each triangular element in the two-dimensional measurement grid, the coordinates of its three vertices are extracted in turn. The vertex coordinates are derived from the node set within the projected boundary in the subdivision process, and the coordinate values are in the local two-dimensional rectangular coordinate system established by the measurement reference plane, usually expressed as floating-point values. For any triangular element, its area calculation can use the classical plane geometry area formula, that is:

[0087] ;

[0088] where (x1, y1), (x2, y2), (x3, y3) are the coordinates of the three vertices of the triangle under the measurement reference plane. The above calculation method has the advantages of strong universality, numerical stability, and easy batch processing, and is suitable for automatic execution in large-scale grid element structures.

[0089] After completing the element area calculation, in order to ensure the spatial accuracy of the area statistical results, each calculated element area result needs to be marked with a spatial position, and a boundary consistency check needs to be performed. The specific operation is as follows: taking the centroid coordinates of each triangular element as the spatial identification point, calling the known polygon boundary structure in the fitted boundary contour, and performing point-in-polygon (point-in-polygon) determination. If the centroid is located in the internal area of the closed boundary contour, the area of the triangular element is counted into the effective statistical range; otherwise, if the centroid falls outside the boundary or in the boundary overlap error band, it should be discarded or further reclassified as appropriate.

[0090] The above spatial consistency check plays a key role in area accuracy. Due to the phenomena of error propagation, boundary fitting not being strict, or edge and corner area subdivision overlapping in the subdivision process, if the spatial attribution of the grid element is not determined, it is easy to cause area overcounting or undercounting. For example, when the boundary contour is curved or composite, some elements generated by subdivision may cross the boundary curve or contain local overlapping areas. If boundary checking is not done, the element area may be mistakenly counted as a "legal measurement area", affecting the accuracy of the overall result.

[0091] After completing the spatial position determination, the area values of all grid elements that pass the determination are processed one by one. The area accumulation is performed in a linear summation manner, which can be executed in the order of element number or spatial partition order, and the total area value can be represented as:

[0092] ;

[0093] where, represents the area of the i-th triangle mesh element passing the boundary check, and n is the total number of effective elements passing the screening. The total area value is taken as the final measurement result of the red line outer expansion area, has the characteristics of boundary closure control, projection coordinate consistency and mesh structure traceability, and is convenient for comparison, connection and result verification with cadastral map, planning line, land occupation license and other information.

[0094] Preferably, the method further comprises performing measurement result output, including: combining the measured total area with the corresponding boundary coordinates into a planar area object, and exporting in GeoJSON or Shapefile format; generating a metadata file related to the measurement, the metadata file including acquisition time, point cloud density, attitude compensation parameters and projection plane definition; wherein the planar area object and the metadata file together constitute a structured surveying and mapping output result output.

[0095] In the embodiment of the application, after completing the area measurement of the red line outer expansion area, in order to realize the standardized management and cross-platform use requirements of the measurement results, the calculation results and related data need to be structured and packaged and output to a data format with a universal data interface to form a surveying and mapping result file set that can be called and reused for a long time. This process not only includes the output of the total area and boundary data which are the core results of the measurement, but also includes the metadata archiving of key control parameters and data processing constraints and other information in the measurement task process, to ensure that the source of the results is traceable, the calculation process is traceable, and the output results are analyzable.

[0096] Specifically, the measured total area of the red line outer expansion area is combined with the corresponding closed boundary contour coordinates to construct a standard planar area object. The planar area object takes the closed boundary contour as the geometric outer shape boundary, takes the total area value as an additional attribute field, and contains the spatial sequence information of the contour points, to ensure that its topological structure has consistent expression in various geographic information platforms. The object can be output as a GeoJSON or Shapefile format file according to the use requirements, wherein the GeoJSON format is suitable for lightweight interaction and map browser embedding on the Web side, and the Shapefile format is suitable for loading, analysis and spatial database management in the traditional GIS software environment.

[0097] When the planar area object is generated, a metadata file associated with the current measurement process needs to be constructed to record the spatial control parameters and processing state information involved in the measurement task. The metadata file includes but is not limited to the following field contents: acquisition time (used to indicate the timestamp of the point cloud data acquisition), point cloud density (used to express the spatial coverage accuracy), attitude compensation parameter (used to explain the initial attitude matrix or inertial navigation correction model adopted for point cloud data attitude correction), projection plane definition (used to clearly define the local coordinate system parameters such as origin coordinates, principal axis direction, projection type, etc. for boundary contour projection). In addition, auxiliary information such as measurement area number, operator identification, data processing version number, etc. can be recorded to improve the attribution management capability of the surveying and mapping data.

[0098] Finally, the above planar area object and metadata file are associated and packaged to form a structured surveying and mapping output result. This result can be used as a basic survey area unit and directly connected to the railway asset management system, land use review platform or local planning archive to realize the archiving, review and visual tracking of the survey area data. The structured output not only improves the data integrity and interoperability of the measurement results, but also lays a standard data foundation for the system call of the survey area results in actual management, approval, inspection and other links, and has strong application promotion value.

[0099] Figure 3 is a system structure diagram of a railway line surrounding area area surveying and mapping system based on a UAV provided by an embodiment of the present application. As shown in Figure 3 The embodiment of the present application provides a railway line surrounding area area surveying and mapping system based on a UAV, which comprises: an acquisition unit for performing coordinate registration processing on laser point cloud data collected by a UAV and a railway red line vector map to obtain standard point cloud data and a red line reference boundary in a unified coordinate system; a fitting unit for extracting edge point sets of an actual occupied area outside the red line based on the standard point cloud data and the red line reference boundary, and fitting to obtain a closed boundary contour; a processing unit for performing unified plane projection and subdivision processing based on the fitted boundary contour to generate a two-dimensional measurement grid for area determination; and an output unit for accumulating unit areas based on the two-dimensional measurement grid and outputting the total area of the extended area outside the red line and the corresponding boundary coordinates.

[0100] The embodiment of the present application further provides a computer readable storage medium, which stores instructions thereon, and the instructions make the computer execute the above-mentioned railway line surrounding area area surveying and mapping method based on a UAV when the computer runs.

[0101] Those skilled in the art can understand that all or part of the steps of the method for implementing the above-mentioned embodiments can be completed by programs instructing relevant hardware, the programs are stored in a storage medium, and the programs include a plurality of instructions for enabling a single-chip microcomputer, a chip or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various storage media capable of storing program codes.

[0102] The optional embodiments of the present application are described in detail above in combination with the drawings, but the embodiments of the present application are not limited to the specific details in the above-described embodiments. Within the technical concept scope of the embodiments of the present application, various simple modifications can be made to the technical solutions of the embodiments of the present application, and these simple modifications all belong to the protection scope of the embodiments of the present application. In addition, it should be noted that each specific technical feature described in the above-described specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the embodiments of the present application will not be described again for various possible combinations.

[0103] In addition, various different embodiments of the present application can also be combined in any manner, as long as it does not deviate from the idea of the embodiments of the present application, and it should also be considered as disclosed by the embodiments of the present application.

Claims

1. A method for surveying the area of the surrounding region along the railway based on a UAV, characterized by, The method comprises: Performing coordinate registration processing on the laser point cloud data collected by the unmanned aerial vehicle and the railway red line vector map to obtain standard point cloud data and red line reference boundary in a unified coordinate system, including: Obtaining time-synchronized position information output by a global positioning system carried by the unmanned aerial vehicle platform and flight attitude data output by an inertial navigation system, performing time synchronization on the time-synchronized position information and the flight attitude data to obtain a complete spatial pose trajectory of the aircraft during laser scanning; Based on the complete spatial pose trajectory of the aircraft during laser scanning, combined with the ranging angle, emission direction and echo intensity information recorded by the laser radar, the original relative coordinates of each laser dot in the three-dimensional space are constructed, and the original relative coordinates are subjected to three-dimensional rigid body transformation based on the position provided by the global positioning system and the attitude angle provided by the inertial navigation system, to complete the attitude compensation and geographical position calculation of each measurement point in the point cloud, and obtain the point cloud data after attitude correction; Performing geographical projection transformation on the corrected point cloud data to convert the coordinate system of the corrected point cloud data to be consistent with the coordinate reference adopted by the railway red line vector map; After completing the projection conversion, the point cloud data and the railway red line vector map are superimposed, spatial coordinate alignment verification is performed, and it is confirmed that the position error of the two types of data in the boundary abutting area is within a preset tolerance range. If there is a preset deviation, fine adjustment is performed based on the common control points or boundary coincidence degree, and finally the standard point cloud data and the red line reference boundary in the unified coordinate system are generated; Based on the standard point cloud data and the red line reference boundary, the edge point set of the actual occupied area outside the red line is extracted, and a closed boundary contour is fitted; Based on the fitted boundary contour, unified plane projection and subdivision processing are performed to generate a two-dimensional measurement grid for area determination; Based on the two-dimensional measurement grid, the areas of the units are accumulated and the total area and the corresponding boundary coordinates of the extended area outside the red line are output. 2.The unmanned aerial vehicle based railway line perimeter area mapping method of claim 1, wherein, Based on the standard point cloud data and the red line reference boundary, the edge point set of the actual occupied area outside the red line is extracted, including: Based on the standard point cloud data, the elevation difference of each measurement point relative to its neighborhood points is determined, and a point cloud elevation difference gradient map is constructed; Based on the point cloud elevation difference gradient map, positions with an elevation difference greater than a preset difference threshold are taken as an edge candidate point set; The spatial relationship between the edge candidate point set and the red line reference boundary is judged, and measurement points located outside the red line and having an elevation difference greater than the preset difference threshold relative to their neighborhood points are screened out to form an edge point set. 3.The UAV-based method of claim 2, wherein, The fitting rule of the closed boundary contour is: The edge point set is sorted according to the curvature perception in two-dimensional space coordinates, and the edge path fitting is performed based on the smooth closed interpolation algorithm with minimum curvature change to form a closed boundary contour; wherein, If the sorted edge point set does not form a closed boundary contour, a shortest connection segment between the beginning and the end is introduced in the fitting process to complete the edge path fitting to form a closed boundary contour. 4.The UAV-based method of mapping the area of the region along the railway according to claim 1, wherein, Based on the fitted boundary contour, unified plane projection and subdivision processing are performed, including: The main axis direction of the fitted closed boundary contour is calculated, and a local measurement reference plane is constructed based on the main axis direction; wherein, The measurement reference plane takes the geometric center point of the boundary contour as the origin and the main shaft direction as the X-axis direction to establish a two-dimensional plane rectangular coordinate system; Transform all boundary point coordinates in the closed boundary contour to the measurement reference plane to obtain a projection contour of the boundary contour under the corresponding two-dimensional coordinate system; Based on the set of boundary point coordinates in the projection contour, a minimum circumscribed rectangular region containing all the projection points is calculated, and the circumscribed rectangular region is taken as a spatial boundary constraint for the measurement grid division, used to limit the spatial range of the measurement region. 5.The UAV-based method of mapping the area of the region along the railway according to claim 4, wherein, The generation rule of the two-dimensional measurement grid is: Within the minimum circumscribed rectangular range, the projection contour boundary is taken as a mandatory constraint boundary, and a Delaunay triangulation algorithm is executed to generate a two-dimensional measurement grid cell covering the inside of the closed boundary; wherein, A grid quality factor is introduced for each triangulation cell in the Delaunay triangulation algorithm for quality control to eliminate degenerate cells that do not meet the preset minimum angle requirement. 6.The UAV-based method of mapping the area of the region along the railway according to claim 5, wherein, Based on the two-dimensional measurement grid, the areas of the cells are accumulated and the total area and corresponding boundary coordinates of the red line expansion region are output, including: For each triangular cell in the two-dimensional measurement grid, the corresponding vertex coordinates are obtained and the cell area is calculated according to the plane geometric rule to obtain the cell area of the corresponding measurement grid; The total area is sequentially accumulated by adding the cell areas of all measurement grids; wherein, Before sequentially accumulating the total area by adding the cell areas of all measurement grids, the cell area calculation results of each measurement grid are spatially labeled and associated with the closed boundary contour for verification to ensure that all area results fall within the boundary range. 7.The UAV-based method of mapping the area of the region along and adjacent to the railway according to claim 1, wherein, The method further includes outputting the measurement results, including: Combining the measured total area and the corresponding boundary coordinates into a planar region object and exporting it in GeoJSON or Shapefile format; Generating a metadata file related to this measurement, which includes the collection time, point cloud density, attitude compensation parameters, and projection plane definition; wherein, The planar region object and the metadata file together constitute the structured surveying and mapping output result.

8. A drone-based system for mapping the area of the surrounding region along the railway line, characterized in that, The system is used to execute the unmanned aerial vehicle-based railway line surrounding area area surveying and mapping method of any one of claims 1-7, and the system includes: The acquisition unit is used to perform coordinate registration processing on the laser point cloud data collected by the unmanned aerial vehicle and the railway red line vector map to obtain standard point cloud data and red line reference boundaries in a unified coordinate system; The fitting unit is used to extract the edge point set of the actual occupied area outside the red line based on the standard point cloud data and the red line reference boundaries, and fit to obtain a closed boundary contour; The processing unit is used to perform unified plane projection and division processing based on the fitted boundary contour to generate a two-dimensional measurement grid for area determination; The output unit is used to accumulate the areas of the cells based on the two-dimensional measurement grid and output the total area and corresponding boundary coordinates of the red line expansion region.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores instructions which, when executed on the computer, cause the computer to perform the method for surveying the area of the surrounding region along the railway based on the unmanned aerial vehicle according to any one of claims 1-7.

Images