Automatic lighting generation method based on airport regulations AIP and satellite image analysis

Abstract

This invention relates to the field of airport lighting generation and control, and addresses the challenges of massive workload, low efficiency, and difficulty in ensuring accuracy in automatic lighting generation methods based on airport regulations (AIP) and satellite image analysis. [Solution] The system analyzes the AIP document to extract geometric topology information of runways and taxiways, extracts boundary point clouds from the corresponding satellite images, and if the deviation between the principal axis direction and the magnetic azimuth angle exceeds a threshold, generates a pavement network based on the satellite point cloud, constructs a dynamic buffer region based on the runway endpoints, fuses the AIP criteria, and directly aligns the satellite boundary point clouds to the coordinate system where the geometric topology information is located. Lighting nodes are placed in straight and curved sections, lighting attributes are associated with the nodes based on a standard rule library, the nodes are activated by combining airport operation mode and simulation training requirements, generates airport lighting configuration data for the flight simulator view system, and achieves automated, high-precision lighting generation.

Description

Technical Field

[0001] The present invention belongs to the field of airport light generation and control, and specifically relates to an automatic light generation method based on airport regulations AIP (Aeronautical Information Publication) and satellite image analysis.

Background Art

[0002] Airport lighting is the foundation of aviation safety and the key to operational efficiency. It provides indispensable visual reference for aircraft take-off, landing and ground movement in complex environments, and provides important visual guidance for pilots at night or under low visibility conditions, so as to accurately align the aircraft with the runway, ensure safe landing and take-off, and prevent runway incursion, overrun or deviation from taxiways.

[0003] In flight training, the visual scene system of a flight simulator reproduces the lighting system with high fidelity to provide pilots with realistic training scenarios, thereby helping pilots repeatedly train core maneuvering capabilities, procedure application and special situation handling in complex weather and night conditions in a risk-free environment, and plays an extremely important role in flight simulation training.

[0004] At the current stage, the production of lights completely depends on manual work, and the workload is enormous. Each airport needs to arrange a large number of lights. At the same time, airport lighting is complex. For example, the color of lights varies according to the distance from the end of the runway, and errors are inevitable only with pure manual modeling. Situations such as missing production, excessive production, and wrong color settings can also occur. At the same time, although there are certain standards for the spacing of lights (for example, 60 meters for runway edge lights), these accurate values cannot be guaranteed, and it is difficult to maintain accuracy to a certain extent.

[0005] Based on this, the present invention proposes an automatic light generation method based on airport regulations AIP and satellite image analysis. [Overview of the Initiative] [Means for solving the problem]

[0006] In order to solve the above-mentioned problems in conventional technology, namely the enormous amount of work involved in modeling airport lighting, the resulting decrease in efficiency, the high likelihood of errors, and the difficulty in ensuring accuracy, the present invention provides an automatic lighting generation method based on airport regulations AIP and satellite image analysis, Step S10 involves analyzing the airport AIP document to extract geometric topology information of the runway and taxiway, including at least the runway endpoint, runway centerline, pavement width, magnetic azimuth angle, and approach light type identifier. Step S20 involves acquiring satellite remote sensing images corresponding to the positions of runways and taxiways, extracting image boundary point clouds, determining whether the deviation between the principal axis direction and magnetic azimuth angle of the satellite boundary point cloud exceeds a preset angular threshold, proceeding to step S30 to execute a ruling strategy if it exceeds the threshold, and proceeding to step S40 if it does not exceed the threshold. Step S30 generates a pavement topology network based on satellite boundary point clouds, constructs a dynamic buffer region based on runway endpoints, maps nodes within the buffer region to the AIP reference pavement surface, maintains the original topology for nodes outside the buffer region, outputs a fused pavement spatial reference network, and proceeds to step S50. Step S40 involves directly aligning the satellite boundary point cloud with the coordinate system where the geometric topology information is located, outputting a fused pavement surface spatial reference network, and proceeding to step S50. Step S50 involves installing lighting nodes in straight sections within the pavement surface spatial reference network based on a preset interval threshold, and installing lighting nodes in curved sections within the pavement surface spatial reference network based on the radius of curvature of the curved sections. Step S60 involves associating lighting attributes with lighting nodes corresponding to different pavement surfaces based on a standard rule library, activating the lighting nodes according to the rule set corresponding to the requirements of the airport operation mode and flight simulation training scenario, and generating airport lighting configuration data to drive the flight simulator viewing system. including, This invention provides an automatic lighting generation method based on airport regulations (AIP) and satellite image analysis.

[0007] Furthermore, the method for calculating the main axis direction of the satellite boundary point cloud is: The steps include: calculating a covariance matrix for the satellite boundary point cloud, determining the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, using the eigenvector corresponding to the largest eigenvalue as the principal axis direction vector, calculating the principal axis azimuth angle based on the principal axis direction vector, and setting this as the principal axis direction of the satellite boundary point cloud; Includes.

[0008] Furthermore, the steps of acquiring satellite remote sensing images corresponding to the locations of runways and taxiways and extracting image boundary point clouds are specifically as follows: The steps include: segmenting the aforementioned satellite remote sensing image into cloud layers and vegetation-obscuring regions using a convolutional neural network; geometrically correcting the segmented satellite remote sensing image based on a pre-constructed digital elevation model of runways and taxiways; and extracting the image boundary point cloud of the geometrically corrected satellite remote sensing image. Includes.

[0009] Furthermore, the aforementioned arbitrage strategy specifically, The steps include: constructing a triangulation network according to the satellite boundary point cloud; removing connected edges from the triangulation network whose deviation in the perpendicular angle with respect to the runway direction exceeds a predetermined threshold; extracting the maximum connected region of the remaining triangulation network; and identifying nodes associated with geometric topology information within the maximum connected region as key nodes. The process involves generating a circular buffer region with a dynamic radius centered on the runway endpoint, mapping key nodes within the buffer region to a reference pavement surface defined in the airport AIP document, and maintaining the original spatial coordinates for key nodes outside the buffer region. The steps include: fusing the mapped nodes with the original nodes to generate a calibrated pavement surface spatial reference network; Includes.

[0010] Furthermore, a method for directly aligning satellite boundary point clouds with the coordinate system where geometric topology information is located and outputting a fused pavement surface spatial reference network is: The steps include performing an affine transformation on the satellite boundary point cloud and superimposing the principal axis direction of the satellite boundary point cloud onto the magnetic azimuth angle, The process involves performing least-squares fitting based on the runway center point, translating the affine-transformed satellite boundary point cloud to the pavement area defined in the airport AIP document, and maintaining the topological connectivity of the transformed satellite boundary point cloud invariantly. Includes.

[0011] Furthermore, the step of installing lighting nodes in a straight section based on a predetermined interval threshold, as described above, specifically involves: The steps include: extracting a set of centerlines for all straight sections from the pavement surface spatial reference network, calculating the actual length for each centerline of a straight section, and determining the extension direction vector; The process involves calculating a sequence of light node positions along the extension direction of a straight section according to the principle of equal spacing, based on a pre-set interval threshold, and generating an initial set of straight section light nodes that includes all straight section light nodes. The steps include: outputting the initial set of linear light nodes to the light topology network generation module, Includes.

[0012] Furthermore, the aforementioned step of installing lighting nodes in the curved section based on the radius of curvature is, specifically, The process involves extracting the centerline set and corresponding radius of curvature attribute values ​​for all curved sections from the pavement surface spatial reference network, calculating a dynamic node density adjustment coefficient according to the radius of curvature value of each curved section, and determining that the node density increases as the radius of curvature decreases. The steps include determining the adaptive node interval value of the curve section based on a pre-set interval threshold and a dynamic node density adjustment coefficient, The steps include generating a curved light node position sequence according to adaptive node spacing values ​​along the curved centerline, The steps include generating and outputting a set of curved light nodes that include all curved section light nodes, Includes.

[0013] Furthermore, the process further includes an intersection node generation step, wherein the intersection node generation step is: The steps include: integrating the initial set of straight light nodes and the set of curved light nodes to form a base set of light nodes, and performing triangular mesh division on the intersection area within the pavement surface spatial reference network based on its boundary nodes; The steps include: extracting all vertices generated by triangular mesh division as a set of intersecting ignition nodes, and fusing the base ignition node set with the intersecting ignition node set to generate a complete ignition topology network; The steps include outputting the complete lighting topology network to the dynamic rule engine module, Includes.

[0014] Furthermore, the step of associating the lighting attribute with a lighting node corresponding to a different pavement surface is, The steps include loading a standard rule library, creating an airport rule database that includes a daytime mode rule set, a nighttime mode rule set, and a special situation mode rule set, and the special situation mode rule set includes at least a predefined emergency situation, The steps include classifying and associating lighting nodes within the pavement surface spatial reference network into runway section node sets, taxiway section node sets, and intersection node sets, forming a corresponding light attribute template for the node set of each classification, wherein the light attribute template includes a color attribute, a flashing frequency attribute and a brightness level attribute; outputting a light node database with defined attributes to a rule activation module; comprising the above steps.

[0015] further, the step of activating light nodes according to a rule set corresponding to requirements of an airport operation mode and a flight simulation training scenario, and generating airport light configuration data for driving a visual scene system of a flight simulator specifically comprises: receiving an airport operation mode command, and matching the command with a corresponding rule set in an airport rule database; detecting attribute conflict nodes based on a rule conflict resolver, generating a conflict node list, performing priority judgment on the conflict node list, and outputting a conflict resolution decision table; activating light node attributes according to the conflict resolution decision table, and generating airport light configuration data for driving a visual scene system of a flight simulator; comprising the above steps.

Effects of the Invention

[0016] Beneficial effects of the present invention are as follows.

[0017] (1) Through automated analysis of AIP documents and satellite remote sensing images, automatic laying of light nodes and association of light attributes are performed based on a fused pavement space reference network, which fundamentally innovates the method of manually arranging lights one by one, greatly shortens the construction time of an airport light model, and significantly reduces human costs.

[0018] (2) By automatically associating lighting attributes based on a standard rule library, problems such as color errors, missing or duplicate lighting placements, and other issues that may occur when humans make rule judgments regarding distance, color, etc., were avoided. By placing lighting nodes based on pre-set interval thresholds and curvature radius calculations, accurate compliance with important standards such as 60-meter intervals for runway edge lights was strictly ensured, overcoming the challenges of achieving high accuracy with manual measurement and placement. By adopting a strategy of fusing AIP geometric information and satellite imagery and setting angular deviation thresholds to perform intelligent rulings, a high degree of conformity between the generated lighting layout and the actual airport pavement surface spatial standards was effectively ensured.

[0019] (3) The final generated airport lighting configuration data is specifically designed to drive the flight simulator visual system and can dynamically activate lighting nodes in response to the requirements of the flight simulation training scenario (e.g., specific weather, nighttime, special conditions). This provides pilots with a highly fidelity, norm-compliant, and flexibly configurable lighting visual environment in the simulator, directly enabling safe and efficient training in high-risk subjects such as dealing with complex weather, nighttime, and special conditions, while ensuring the authenticity and effectiveness of the training scenarios. [Brief explanation of the drawing]

[0020] Other features, purposes, and advantages of the present application will become more apparent through a detailed description of non-limiting embodiments made below with reference to the drawings. [Figure 1] This is a schematic flowchart of the automatic lighting generation method based on airport regulations AIP and satellite image analysis according to the present invention. [Modes for carrying out the invention]

[0021] The present invention will be described in more detail below, combining drawings and embodiments. It should be understood that the specific embodiments described here are merely for interpreting the related invention and do not limit the present invention. Furthermore, for the sake of clarity, only the parts relating to the related invention are shown in the drawings.

[0022] Furthermore, the embodiments and features described herein can be combined with each other, provided that no contradictions arise. The present application will now be described in detail in combination with the embodiments, with reference to the drawings.

[0023] The present invention is an automatic lighting generation method based on airport regulations AIP and satellite image analysis, Step S10 involves analyzing the airport AIP document to extract geometric topology information of the runway and taxiway, including at least the runway endpoint, runway centerline, pavement width, magnetic azimuth angle, and approach light type identifier. Step S20 involves acquiring satellite remote sensing images corresponding to the positions of runways and taxiways, extracting image boundary point clouds, determining whether the deviation between the principal axis direction and magnetic azimuth angle of the satellite boundary point cloud exceeds a preset angular threshold, proceeding to step S30 to execute a ruling strategy if it exceeds the threshold, and proceeding to step S40 if it does not exceed the threshold. Step S30 generates a pavement topology network based on satellite boundary point clouds, constructs a dynamic buffer region based on runway endpoints, maps nodes within the buffer region to the AIP reference pavement surface, maintains the original topology for nodes outside the buffer region, outputs a fused pavement spatial reference network, and proceeds to step S50. Step S40 involves directly aligning the satellite boundary point cloud with the coordinate system where the geometric topology information is located, outputting a fused pavement surface spatial reference network, and proceeding to step S50. Step S50 involves installing lighting nodes in straight sections within the pavement surface spatial reference network based on a preset interval threshold, and installing lighting nodes in curved sections within the pavement surface spatial reference network based on the radius of curvature of the curved sections. Step S60 involves associating lighting attributes with lighting nodes corresponding to different pavement surfaces based on a standard rule library, activating the lighting nodes according to the rule set corresponding to the requirements of the airport operation mode and flight simulation training scenario, and generating airport lighting configuration data to drive the flight simulator viewing system. including, This invention provides an automatic lighting generation method based on airport regulations (AIP) and satellite image analysis.

[0024] To more clearly explain the automatic lighting generation method based on airport regulations AIP and satellite image analysis according to the present invention, each step in an embodiment of the present invention will be described in detail below with reference to Figure 1.

[0025] The first embodiment of the present invention, an automatic lighting generation method based on airport regulations AIP and satellite image analysis, includes steps S10 to S60, and a detailed description of each step is as follows.

[0026] In step S10, the airport AIP document is analyzed to extract geometric topology information of the runway and taxiway, including at least the runway endpoints, runway centerline, pavement width, magnetic azimuth angle, and approach lighting type identifier.

[0027] In this embodiment, AIP documents are processed using a dedicated document analysis engine. For example, based on an XML parsing library or a specific aviation data analysis API, the engine can identify and read specific data fields or labels that define the geometric features of runways and taxiways within the document. During the analysis process, it is necessary to accurately identify and extract the following important information: Runway endpoints: The latitude and longitude coordinates or projected coordinates of both ends of each runway are accurately obtained, which serve as reference points for determining the spatial position and orientation of the runway. Runway centerline: Geometric information of the straight section connecting the two endpoints of the runway, or a sequence of centerline points including the midpoint, is extracted and used to determine the precise orientation and length of the runway. Pavement width: The design width values ​​for each runway and taxiway are extracted. This data is extremely important in calculating the placement of subsequent lighting (for example, the offset amount from the centerline of runway edge lights). Magnetic azimuth angle: The numerical value of the magnetic azimuth angle for each runway is extracted, representing the magnetic north direction of the runway centerline, and providing a directional reference for alignment with subsequent satellite images or for coordinate system transformation. Approach lighting type identifier: Identify and extract the type code of the approach lighting system associated with each end of the runway (e.g., "ALSF-I", "CALVERT", "SSALR", etc.). This identifier is directly relevant to the selection of approach lighting configuration rules in subsequent steps.

[0028] The analyzed and extracted information is compiled into a structured geometric topology data model. This model can clearly represent the spatial location (endpoint coordinates), geometric shape (centerline, width), direction (magnetic azimuth angle), and key attributes (approach lighting type) of runways and taxiways. The output of this step is a structured dataset containing the basic information of all runways and taxiways, providing an accurate and aeronautically compliant reference geometric frame for subsequent steps (particularly fusion with satellite imagery and placement of lighting nodes).

[0029] In step S20, satellite remote sensing images corresponding to the positions of the runway and taxiway are acquired, and an image boundary point cloud is extracted. It is determined whether the deviation between the principal axis direction and the magnetic azimuth angle of the satellite boundary point cloud exceeds a preset angular threshold. If it exceeds the threshold, the process proceeds to step S30 to execute the arbitration strategy; otherwise, the process proceeds to step S40.

[0030] In this embodiment, the steps of acquiring satellite remote sensing images corresponding to the positions of runways and taxiways and extracting image boundary point clouds are specifically as follows: The steps include: segmenting the aforementioned satellite remote sensing image into cloud layers and vegetation-obscuring regions using a convolutional neural network; geometrically correcting the segmented satellite remote sensing image based on a pre-constructed digital elevation model of runways and taxiways; and extracting the image boundary point cloud of the geometrically corrected satellite remote sensing image. Includes.

[0031] Here, based on the position coordinates of the runway and taxiway acquired in step S10, the original satellite remote sensing image of the corresponding area is retrieved from the satellite image library. To eliminate interference from the environment, semantic segmentation is performed on the image using a trained convolutional neural network (CNN), automatically identifying and masking occluded areas to ensure that the extraction of the pavement contour is not affected by interference.

[0032] Geometric correction is performed on segmented satellite images by combining them with pre-constructed digital elevation models of runways and taxiways. The digital elevation models of runways and taxiways may be constructed based on DEMs generated from LiDAR point clouds, but this is prior art and therefore a detailed explanation is omitted. The geometric correction includes performing spatial correction based on the alignment of the image's geographic coordinates with the elevation model, and calculating a perspective projection transformation matrix using elevation data based on the principle of collinearity conditions. This eliminates perspective distortion of the image caused by terrain relief and sensor inclination, and generates orthorectified images with geometric accuracy reaching sub-meter levels.

[0033] The corrected orthorectified image is then subjected to pavement contour extraction. Specifically, the Canny operator or a deep edge detection model is used to extract runway / taxiway boundaries, and the consecutive boundaries are ordered into an image boundary point cloud. Convert to TIFF0007920487000002.tif627.

[0034] In this embodiment, the method for calculating the satellite boundary point cloud in the direction of the principal axis is as follows: The steps include: calculating a covariance matrix for the satellite boundary point cloud, determining the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, using the eigenvector corresponding to the largest eigenvalue as the principal axis direction vector, calculating the principal axis azimuth angle based on the principal axis direction vector, and setting this as the principal axis direction of the satellite boundary point cloud; Includes.

[0035] Here, the image boundary point group The method for constructing the covariance matrix C based on JPEG0007920487000003.jpg612 is: The file is JPEG0007920487000004.jpg1145, and here, TIFF0007920487000005.tif615, TIFF0007920487000006.tif514 is a coordinate distribution, TIFF0007920487000007.tif618 is a covariance.

[0036] Perform eigenvalue decomposition on matrix C and eigenvalue TIFF0007920487000008.tif65 and TIFF0007920487000009.tif76 and its corresponding eigenvectors TIFF0007920487000010.tif66, Retrieve TIFF0007920487000011.tif77, The filename is JPEG0007920487000012.jpg815.

[0037] Maximum eigenvalue Eigenvectors corresponding to TIFF0007920487000013.tif75 JPEG0007920487000014.jpg725 is used as the principal axis direction vector of the boundary point cloud, and the components of the direction vector are The principal axis azimuth angle is determined by the arctangent function according to JPEG0007920487000015.jpg713. JPEG0007920487000016.jpg751 is calculated, and here, TIFF0007920487000017.tif65 is the component of the direction vector on the horizontal axis (X-axis) of the image coordinate system. TIFF0007920487000018.tif77 contains the component of the direction vector along the vertical axis (Y-axis) of the image coordinate system.

[0038] Principal axis azimuth TIFF0007920487000019.tif76 and the pre-set magnetic azimuth angle Absolute deviation with TIFF0007920487000020.tif66 The value TIFF0007920487000021.tif66 is calculated, and it is determined whether the absolute deviation exceeds a preset angle threshold. The preset angle threshold is between 0.1° and 2°, and in this embodiment, 1° is preferred.

[0039] In step S30, a pavement topology network is generated based on satellite boundary point clouds, a dynamic buffer region is constructed with runway endpoints as the reference point, nodes within the buffer region are mapped to the AIP reference pavement surface, the original topology is maintained for nodes outside the buffer region, a fused pavement spatial reference network is output, and the process proceeds to step S50.

[0040] In this example, the arbitrage strategy is specifically: The steps include: constructing a triangulation network according to the satellite boundary point cloud; removing connected edges from the triangulation network whose angular deviation from the direction perpendicular to the runway direction exceeds a predetermined threshold; extracting the maximum connected region of the remaining triangulation network; and identifying nodes associated with geometric topology information within the maximum connected region as key nodes. The process involves generating a circular buffer region with a dynamic radius centered on the runway endpoint, mapping key nodes within the buffer region to a reference pavement surface defined in the airport AIP document, and maintaining the original spatial coordinates for key nodes outside the buffer region. The steps include: fusing the mapped nodes with the original nodes to generate a calibrated pavement surface spatial reference network; Includes.

[0041] In this embodiment, when it is determined in step S20 that the deviation between the principal axis direction of the satellite image and the AIP magnetic azimuth angle exceeds a limit value, the arbitration strategy is activated, which includes the following:

[0042] In step S20, AIP geometric topology information including the satellite boundary point cloud extracted and the runway endpoint coordinates analyzed in S10 is obtained. Constrained Delaunay triangulation is performed on the satellite boundary point cloud to construct a triangulated mesh network covering the pavement area, where mesh nodes are boundary points and connecting edges represent pavement topological relationships.

[0043] To eliminate the impact of rotational distortion on the topological structure of satellite images, directional filtering is performed, which includes calculating edge direction angles, removing abnormal edges, and extracting the maximum connected region.

[0044] Here, the method for calculating the side direction angle is: Each edge within the triangular mesh Regarding TIFF0007920487000022.tif66, the angle between the AIP runway centerline and the surrounding area. The step of calculating the side direction angle using TIFF0007920487000023.tif67, Includes.

[0045] In the aforementioned triangulation network, connection edges whose deviation in the perpendicular angle with respect to the runway direction exceeds a preset threshold are removed. Here, the preset threshold is preferably 15° in this embodiment, and specifically, JPEG0007920487000024.jpg626 If a preset threshold is met, i.e., if an edge is not approximately perpendicular to the runway direction, that edge is deleted, and the maximum connected subgraph consisting of the remaining edges is retained. This set of nodes is defined as a key node, and the key node includes at least runway endpoints, taxiway intersections, etc.

[0046] In this embodiment, a circular buffer region is generated centered on the runway endpoint defined in the AIP document, with a dynamically expanding radius. The radius of the buffer region is dynamically set according to a multiple of the actual runway width, and in this embodiment, it is set to three times the pavement width to ensure coverage of critical areas at the runway ends. For key nodes located within the buffer region, their spatial coordinates are mapped by perpendicular projection onto the AIP reference pavement surface (e.g., runway centerline or taxiway design centerline), while nodes outside the buffer region retain their original satellite image coordinates, preserving the authenticity of the local topology. This region-specific mapping strategy achieves a delicate balance, ensuring that core regions strictly adhere to aviation standards while non-core regions retain the measured geographical features.

[0047] The buffer region nodes after calibration and the nodes outside the original buffer region are spatially merged, and the pavement topology network is reconstructed based on the node connection relationships. The resulting merged pavement spatial reference network inherits the normative nature of the AIP data while integrating the field features of satellite imagery to form a high-precision spatial reference frame for lighting installation. This network then proceeds directly to step S50, driving the subsequent automated installation process of lighting nodes.

[0048] In this embodiment, the fused pavement surface spatial reference network is a vectorized structural model jointly composed of spatial node sets, topological connection relationships, and pavement surface attribute labels. Its core elements include the following: Calibration nodes are critical points located within the dynamic buffer area at the runway end (e.g., runway entrance, taxiway intersection), whose coordinates are mapped by vertical projection to the reference pavement surface defined by AIP (e.g., runway centerline) to ensure absolute agreement with aviation standards. Original nodes: These are nodes that hold the original coordinates of the satellite image outside the buffer area (e.g., distant taxiways, apron connection points) and maintain the geometric form of the field measurements. Topological connection edges: Based on effective connection relationships after triangulation and directional filtering, accurately represent the connectivity of pavement paths (e.g., runway-taxiway connections, curved turning paths).

[0049] The calibration nodes of the aforementioned pavement surface spatial reference network are associated with runway width, magnetic azimuth angle, and approach lighting type identifiers analyzed from AIP, ensuring that the lighting rule library can accurately recall the reference parameters.

[0050] The original nodes are accompanied by the material type of the pavement surface (asphalt / concrete) and the radius of curvature of the boundary, extracted from satellite imagery, supporting the adaptive calculation of curved light density. All nodes are uniformly represented in either the WGS-84 or UTM coordinate system, eliminating reference differences between data sources.

[0051] The network has been extended with the following functional layers to support flight simulation training scenarios. Operational status indicator: Dynamically indicates the "active / inactive" state of a node. Elevation Reference: Digital elevation model (DEM) data is collected to provide a vertical reference for generating slope lights. Logic division: In accordance with ICAO standards, the area is divided into sub-networks of runway, taxiway, and apron, and differentiated lighting rule sets are driven by these sub-networks.

[0052] In step S40, the satellite boundary point cloud is directly aligned with the coordinate system where the geometric topology information is located, and a fused pavement surface spatial reference network is output, before proceeding to step S50, which is specifically as follows. An affine transformation is performed on the satellite boundary point cloud, and the principal axis direction of the satellite boundary point cloud is superimposed on the magnetic azimuth angle. Least-squares fitting is performed with respect to the runway center point, the satellite boundary point cloud after affine transformation is translated parallel to the pavement area defined in the airport AIP document, and the topological connection relationships of the transformed satellite boundary point cloud are maintained invariantly.

[0053] In this embodiment, the specific steps of the affine transformation are as follows: Construct a rotation matrix R and rotate the point cloud around its centroid. Rotate TIFF0007920487000025.tif510 to perfectly superimpose the axis direction of the satellite image with the AIP magnetic azimuth angle, eliminating directional deviations. After the directional calibration is complete, least-squares fitting is performed with respect to the geometric center point of the runway, which specifically includes the following: The set of polygonal vertices in the runway pavement area defined by AIP. Extract JPEG0007920487000026.jpg710 and rotate the image boundary point cloud. JPEG0007920487000027.jpg57 and Perform point cloud matching on TIFF0007920487000028.tif57. Minimize the translation vector for JPEG0007920487000029.jpg634 Retrieve JPEG0007920487000030.jpg620. The JPEG0007920487000031.jpg67 image is translated horizontally to achieve spatial alignment with the AIP pavement area.

[0054] During the affine transformation (rotation + translation) process, the original topological connection relationships of the satellite boundary point cloud are strictly preserved as follows. The angle and distance ratio of the connecting edges between all adjacent points are kept constant. The geometric shape of the pavement surface contour (e.g., the curvature of the taxiway) is matched to the original satellite image. The converted point cloud is output as node coordinates for a fused pavement surface spatial reference network.

[0055] The satellite boundary point cloud after alignment and AIP geometric topology information (runway endpoints, centerlines, etc.) are integrated as follows. The actual boundary morphology of the pavement surface is represented using satellite point clouds. AIP data provides important reference points for runways. A unified coordinate system is generated to create a fused pavement surface spatial reference network, and the process proceeds to step S50 to drive the installation of lighting nodes.

[0056] In step S50, lighting nodes are installed in straight sections within the pavement surface spatial reference network based on a preset interval threshold, and lighting nodes are installed in curved sections within the pavement surface spatial reference network based on the radius of curvature of the curved sections.

[0057] In this embodiment, the step of installing lighting nodes in a straight section based on a predetermined interval threshold is specifically as follows: The steps include: extracting a set of centerlines for all straight sections from the pavement surface spatial reference network, calculating the actual length for each centerline of a straight section, and determining the extension direction vector; The process involves calculating a sequence of light node positions along the extension direction of a straight section according to the principle of equal spacing, based on a pre-set interval threshold, and generating an initial set of straight section light nodes that includes all straight section light nodes. The steps include: outputting the initial set of linear light nodes to the light topology network generation module, Includes.

[0058] The method for calculating the actual length is as follows: Centerline endpoint coordinates JPEG0007920487000032.jpg714 and If the filename is JPEG0007920487000033.jpg714, then the length is... The filename will be JPEG0007920487000034.jpg953.

[0059] The aforementioned extension direction vector The calculation method for JPEG0007920487000035.jpg74 is as follows: The filename is JPEG0007920487000036.jpg937, and the unitized version of this is The filename will be JPEG0007920487000037.jpg89.

[0060] Lighting nodes are generated according to the principle of equal-spacing distribution, based on a pre-set interval threshold D. Number of nodes The file is JPEG0007920487000038.jpg823, The coordinates of the k-th node are: This becomes TIFF0007920487000039.tif684, and here, The filename is JPEG0007920487000040.jpg732.

[0061] A set of initial straight-line light nodes that cover all straight sections. Generate JPEG0007920487000041.jpg854.

[0062] In this embodiment, the pre-set interval threshold D is specifically as follows: For runway edge lights, taxiway edge lights, and stopway lights, the pre-set interval threshold D is 60 meters, and for taxiway centerline lights, the pre-set interval threshold D is 15 meters.

[0063] The aforementioned step of installing lighting nodes in a curved section based on the radius of curvature is, specifically, The process involves extracting the centerline set and corresponding radius of curvature attribute values ​​for all curved sections from the pavement surface spatial reference network, calculating a dynamic node density adjustment coefficient according to the radius of curvature value of each curved section, and determining that the node density increases as the radius of curvature decreases. The steps include determining the adaptive node interval value of the curve section based on a pre-set interval threshold and a dynamic node density adjustment coefficient, The steps include generating a curved light node position sequence according to adaptive node spacing values ​​along the curved centerline, The steps include generating and outputting a set of curved light nodes that include all curved section light nodes, Includes.

[0064] Here, the set of centerlines and radius of curvature attribute value R of the curved section are extracted from the pavement surface spatial reference network, and the reference radius Combined with JPEG0007920487000042.jpg65, the dynamic node density adjustment coefficient The method for calculating and obtaining JPEG0007920487000043.jpg53 is: The file is JPEG0007920487000044.jpg723, where the smaller R is, JPEG0007920487000045.jpg53 will become larger, and the node density will increase.

[0065] Here, based on a pre-set interval threshold and dynamic node density adjustment coefficient, the adaptive node interval value of the curve section is determined. The method for determining JPEG0007920487000046.jpg69 is: The filename is JPEG0007920487000047.jpg727.

[0066] A sequence of points along the center line of the curve Discretize as JPEG0007920487000048.jpg536 and calculate the cumulative arc length. Adaptive node spacing value based on JPEG0007920487000049.jpg637 Generate a node sequence according to the difference in JPEG0007920487000050.jpg610, and set up a curved light node collection. Output JPEG0007920487000051.jpg79.

[0067] In this embodiment, the intersection node generation step is further included, and the intersection node generation step is The steps include: integrating the initial set of straight light nodes and the set of curved light nodes to form a base set of light nodes, and performing triangular mesh division on the intersection area within the pavement surface spatial reference network based on its boundary nodes; The steps include: extracting all vertices generated by triangular mesh division as a set of intersecting ignition nodes, and fusing the base ignition node set with the intersecting ignition node set to generate a complete ignition topology network; The steps include outputting the complete lighting topology network to the dynamic rule engine module, Includes.

[0068] In this embodiment, the intersection area is the point where the runway and taxiway merge, and with respect to the intersection area, Extract the set of intersection boundary nodes, perform constraint Delaunay triangulation, and create a triangular mesh. Generate JPEG0007920487000052.jpg636, After division, all vertices Extract JPEG0007920487000053.jpg646, and here, JPEG0007920487000054.jpg76 is the coordinates of the j-th vertex, JPEG0007920487000055.jpg69 is the total number of mesh vertices.

[0069] When fusing sets of nodes to generate a complete light topology network, duplicate nodes are removed while topological connections (e.g., the relationships between edges of a triangular mesh) are preserved.

[0070] In step S60, based on a standard rule library, lighting attributes are associated with lighting nodes corresponding to different pavement surfaces, lighting nodes are activated according to rule sets corresponding to the requirements of the airport operation mode and flight simulation training scenario, and airport lighting configuration data is generated to drive the flight simulator viewing system.

[0071] The core objective of this step is to assign precise attributes to the lighting nodes generated in step S50, to dynamically activate the corresponding lighting nodes according to the requirements of different airport operation modes or training scenarios, and ultimately to generate lighting configuration data that can directly drive the flight simulator sight system. The specific implementation process is as follows:

[0072] In this embodiment, the step of associating lighting attributes with lighting nodes corresponding to different pavement surfaces is: The steps include loading a standard rule library, creating an airport rule database that includes a daytime mode rule set, a nighttime mode rule set, and a special situation mode rule set, and the special situation mode rule set includes at least a predefined emergency situation, The steps include classifying and associating lighting nodes within the pavement surface spatial reference network into runway section node sets, taxiway section node sets, and intersection node sets, For each set of nodes in a classification, a corresponding lighting attribute template is constructed, and the lighting attribute template includes color attributes, flashing frequency attributes, and brightness level attributes. The steps include: outputting the attribute-defined light node database to the rule activation module, Includes.

[0073] Here, the configuration rules for the aforementioned lighting attribute template are: This includes associating a white, always-on (fixed-light) light template with the runway centerline node, associating a red, always-on light template with the runway boundary node, associating a blue, flashing light template with the taxiway centerline node, associating a yellow, variable-directional light template with the intersection guidance node, and writing the configured attribute templates to the light node database.

[0074] Specifically, the system first loads the predefined standard rule library ICAO. This rule library contains detailed guidelines for airport lighting under various operating conditions. Based on this rule library, the system constructs a structured airport rule database. This database mainly includes three important rule sets: a daytime mode rule set for simulating daytime operations, a nighttime mode rule set for simulating nighttime and low-visibility operations, and a special situation mode rule set for simulating special operating situations (e.g., emergencies, low-visibility procedures, etc.).

[0075] Next, the system classifies and associates all lighting nodes within the pavement surface spatial reference network into different node sets, mainly runway section node sets (including runway edge lights, centerline lights, etc.), taxiway section node sets (including taxiway edge lights, centerline lights, etc.), and intersection node sets (including guideline lights, etc.), according to their location and function. For each node set in each classification, the system constructs a corresponding lighting attribute template. These attribute templates define in detail the visual characteristics that the node should possess, and include, but are not limited to, the lighting color attribute (e.g., red, white, blue, yellow), flashing frequency attribute (e.g., always on, flashing mode, specific frequency), and brightness level attribute. After the attribute configuration is complete, the system outputs a lighting node database with complete attribute definitions and transmits it to the subsequent rule activation module for processing.

[0076] When configuring lighting attribute templates, the system follows specific rule mapping logic. Specifically, nodes at runway centerline locations are associated with a white, always-on lighting template, representing standard runway centerline light characteristics. Nodes at runway boundary locations are associated with a red, always-on lighting template, representing standard runway edge light characteristics. For taxiway centerline locations, the system associates a blue, flashing lighting template, in accordance with typical taxiway centerline light identification schemes. For guidance nodes in intersection areas, the system simulates the characteristics of indicator lights that guide aircraft turns at intersections and associates a yellow, variable-directional lighting template. All of these configured attribute templates are written to the aforementioned lighting node database.

[0077] In this embodiment, the steps of activating lighting nodes according to a rule set corresponding to the requirements of the airport operation mode and flight simulation training scenario, and generating airport lighting configuration data to drive the flight simulator viewing system, are specifically: The steps include receiving an airport operation mode command and matching it with the corresponding rule set in the airport rule database, The process involves detecting attribute conflict nodes based on a rule conflict resolver, generating a list of conflict nodes, performing priority determination on the list of conflict nodes, and outputting a conflict resolution decision table. The steps include: activating lighting node attributes according to a conflict resolution decision table and generating airport lighting configuration data to drive the flight simulator view system; Includes.

[0078] Identify areas of light nodes where multiple rules are triggered simultaneously. If it is detected that both the red boundary light rule and the white centerline light rule are triggered simultaneously in the runway end area, the actual distance value of that node from the runway end is obtained. If the actual length is ≤ 600 meters, the node will be marked to apply the red light rule. If the actual length is >600 meters, the node should be marked to maintain the white light rule. Output a list of nodes with conflict indicators to the priority determination module.

[0079] If it is necessary to generate a lighting configuration under a specific scenario, the system receives an external airport operation mode command (e.g., "night mode," "low visibility special conditions mode"). Based on the received command, the system matches it with the corresponding rule set (e.g., night mode rule set) from the pre-built airport rule database.

[0080] However, in actual applications, some lighting nodes may be affected by multiple rules or modes simultaneously, resulting in attribute conflicts (for example, a node at the end of the runway belonging to the runway edge lighting area while also being close to the midline lighting rule area). To resolve these conflicts, the system includes a built-in rule conflict resolver. This resolver detects all lighting nodes with attribute conflicts and generates a detailed list of conflicting nodes.

[0081] For each conflicting node in the list, the system executes priority determination logic. For example, if it detects that a node in the runway end area has triggered both the red boundary light rule (runway edge light) and the white centerline light rule simultaneously, the system retrieves the actual distance of that node from the runway end. If this actual distance is 600 meters or less, the node is marked as subject to the red light rule (runway edge light). Conversely, if the actual length is greater than 600 meters, the node is marked as maintaining the white light rule (runway centerline light). This kind of decision logic based on specific position parameters is key to resolving conflicts. Finally, the system outputs a conflict resolution decision table, clearly recording the final attribute rule that each conflicting node should adopt.

[0082] The system strictly follows the instructions in the conflict resolution decision table and activates the attributes of the corresponding nodes in the lighting node database. This means that the attribute values ​​of each lighting node, such as color, flashing frequency, and brightness, are ultimately determined according to the selected rule set and the conflict resolution results. After all node attributes have been activated, the system generates formatted airport lighting configuration data. This data includes the precise spatial location of all lighting nodes and their activated visual attribute information, and is specifically designed to be directly input into and driven by the flight simulator's visual system, thereby accurately and dynamically presenting airport lighting effects in the simulation environment that comply with aviation standards and are adapted to the requirements of specific training scenarios.

[0083] This embodiment further includes the following three-stage fault tolerance feedback mechanism. If geometric-level validation detects a deviation in node spacing, the constraint satisfaction algorithm is triggered to regenerate the node distribution and update the lamp node database. If semantic-level validation detects anomalies in the light's color, the rule engine logs are traced backward to correct the conflict resolution decision table. If a gap in the lighting network is identified during operational-level verification, a replacement node is inserted into the lighting node database and attribute associations are re-executed.

[0084] To ensure that the generated airport lighting configuration data is highly accurate and robust, this embodiment incorporates a specially designed and integrated three-stage fault tolerance feedback mechanism. This mechanism operates throughout the entire process, from the generation of lighting nodes to attribute association and the output of configuration data, providing automated detection, diagnosis, and remediation capabilities for different levels of potential problems. The implementation process is as follows:

[0085] After the lighting nodes have been laid, the system performs a geometric-level verification. The core task of this level is to check the accuracy of the physical spatial distribution of the lighting nodes, in particular to verify whether pre-defined critical spacing criteria (e.g., 60-meter intervals for runway edge lights) are strictly adhered to. The system automatically scans the entire lighting topology network, calculates the actual distance between adjacent nodes, and compares it to a pre-defined spacing threshold. If it detects that the node spacing deviation exceeds the allowable tolerance range (e.g., the system detects that the node spacing for runway edge lights in a certain section is 65 meters instead of the standard 60 meters), the system determines that there is a geometric-level error. At this point, the system immediately triggers its built-in constraint satisfaction algorithm. This algorithm recalculates and optimally generates the lighting node distribution in the problem area based on the geometric constraints of the pavement spatial reference network (e.g., straight section direction, curve curvature) and the spacing rules to be followed, ensuring that the node positions strictly conform to the normative requirements. The corrected node coordinate data is updated in the light node database in real time, replacing the original node data that had the deviation.

[0086] During the association of lighting attributes and the activation of rules, the system performs semantic-level verification. The core task at this level is to ensure that the visual attributes (color, flashing frequency, brightness) assigned to lighting nodes comply with the aeronautical lighting standards logically and semantically, and that the rule activation results are consistent. By analyzing the activated lighting node database, the system identifies potential semantic anomalies, such as a red light appearing where a green light should be in the runway entrance area, or a taxiway centerline light being configured as constantly lit (static) where it should be flashing. If such anomalies in lighting color or operating pattern are detected, the system determines that it is a semantic-level error. To diagnose the cause, the system traces the detailed operation log of the rule engine that processed the node in reverse and analyzes whether it is a rule matching error, a conflict resolution decision error, or an attribute template association error. After identifying the specific cause (for example, if the conflict resolution decision table incorrectly labels a node at the runway end as applying the white centerline light rule instead of the correct red edge light rule), the system automatically corrects the corresponding error entry in the conflict resolution decision table or modifies the attribute association rules, and triggers the rule engine to reprocess the affected nodes to ensure that the final attributes conform to normative semantics.

[0087] After generating the final lighting configuration data, the system performs operational-level verification. The core task at this level is to check the integrity and functionality of the lighting system from the perspective of practical requirements in flight simulation training, to ensure sufficient lighting coverage in all critical pavement areas (especially complex areas such as intersections, high-speed exit taxiways, and waiting positions), and to provide pilots with blind spot-free visual guidance. The system analyzes the distribution map of lighting nodes by combining the structure of the pavement spatial reference network, airport operational rules, and the requirements of the simulation training scenario. If areas with insufficient or missing lighting coverage (i.e., "lighting gaps") are identified, for example, if necessary guidance lights are missing at a connection between a taxiway and a runway, or if the lighting node density is insufficient at the end of a parking apron guidance line, the system determines that this is an operational-level defect. To fill the gaps, the system intelligently inserts supplemental lighting nodes at the identified gap locations according to the topological structure of the pavement network and operational rules (e.g., ICAO Annex 14 criteria). Newly inserted nodes are assigned the initial attribute type that should be present at that location (e.g., yellow guide light) and added to the lighting node database. The system then re-executes the complete attribute association process (i.e., association of lighting attributes in step S60, rule set matching, conflict resolution, etc.) for these new nodes, thereby ensuring that they are correctly configured and activated like other nodes, ultimately forming functionally complete airport lighting configuration data without gaps, thus meeting the requirements of high-fidelity flight simulation training.

[0088] In the above embodiment, each step was described in the order described above, but as those skilled in the art will understand, in order to achieve the effects of this embodiment, the steps do not necessarily have to be performed in this order, and may be performed simultaneously (in parallel) or in reverse order, and all of these simple variations are within the scope of protection of the present invention.

[0089] The automatic lighting generation system based on airport regulations AIP and satellite image analysis according to the second embodiment of the present invention is based on an automatic lighting generation method based on airport regulations AIP and satellite image analysis, and the system is A geometric topology information analysis module configured to analyze airport AIP documents and extract geometric topology information of runways and taxiways, including at least runway endpoints, runway centerlines, pavement width, magnetic azimuth angles, and approach light type identifiers, A deviation determination module is configured to acquire satellite remote sensing images corresponding to the positions of runways and taxiways, extract image boundary point clouds, determine whether the deviation between the principal axis direction and magnetic azimuth angle of the satellite boundary point cloud exceeds a preset angular threshold, and if it exceeds the threshold, switch to a competing module and execute a ruling strategy; otherwise, switch to a non-competing module. A competing module is configured to generate a pavement topology network based on satellite boundary point clouds, construct a dynamic buffer region based on runway endpoints, map nodes within the buffer region to the AIP reference pavement surface, maintain the original topology for nodes outside the buffer region, output a fused pavement surface spatial reference network, and transition to the laying module. A non-conflicting module is configured to directly align satellite boundary point clouds to the coordinate system where geometric topology information resides, output a fused pavement surface spatial reference network, and transition to a laying module. A laying module configured to lay lighting nodes in straight sections of a pavement surface spatial reference network based on a preset interval threshold, and to lay lighting nodes in curved sections of a pavement surface spatial reference network based on the radius of curvature of the curved sections, An attribute configuration module is configured to associate lighting attributes with lighting nodes corresponding to different pavement surfaces based on a standard rule library, activate lighting nodes according to rule sets that meet the requirements of airport operation modes and flight simulation training scenarios, and generate airport lighting configuration data to drive the flight simulator viewing system. It is equipped with.

[0090] For the convenience and brevity of explanation, and so that those skilled in the art can clearly understand, the specific operating processes and related explanations of the system described above can be found in the corresponding processes in the previously mentioned method embodiments and will not be described again here.

[0091] It should be noted that the automatic lighting generation system based on airport regulations AIP and satellite image analysis according to the above embodiment is merely illustrative in the classification of each functional module described above. In actual applications, it is possible to assign the above functions to different functional modules as needed, that is, the modules or steps according to the embodiment of the present invention may be further broken down or combined. For example, the modules of the above embodiment may be integrated into one module to complete all or some of the functions described above, or they may be further divided into multiple submodules. The names of the modules and steps related to the embodiment of the present invention are merely for distinguishing each module or step and should not be considered an unreasonable limitation to the present invention.

[0092] A third embodiment of the present invention is an electronic device, At least one processor, A memory connected to at least one of the processors, The memory stores instructions that can be executed by the processor, and these instructions, when executed by the processor, realize the automatic lighting generation method based on the airport regulations AIP and satellite image analysis described above.

[0093] A fourth embodiment of the present invention is a computer-readable storage medium, the computer-readable storage medium storing computer instructions that, when executed by the computer, realize the above-described airport regulations AIP and automatic lighting generation method based on satellite image analysis. Those skilled in the art will clearly understand that, for the sake of convenience and conciseness of explanation, the specific operating processes and related descriptions of the storage device and processing device described above can be found by referring to the corresponding processes in the previously described embodiment of the method, and will not be repeated here.

[0094] As will be recognized by those skilled in the art, each exemplary module and method step described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both, and the programs corresponding to the software modules and method steps may be stored in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art. To clearly illustrate the compatibility of electronic hardware and software, the above description has already generally described the configuration and steps of each example according to their function. Whether these functions are consequently performed in the form of electronic hardware or software depends on the given application and design constraints of the technical proposal. Those skilled in the art can implement the described functions by using different methods for each given application, but such implementations should not be considered to exceed the scope of the invention.

[0095] Furthermore, terms such as "first," "second," etc., are merely used to distinguish similar objects and are not intended to describe or indicate a specific order or chronological sequence.

[0096] The term “including” or any other similar term is intended to cover non-exclusive inclusion such that a process, method, article or apparatus / device containing a set of elements includes not only those elements but also other elements not explicitly listed, or elements specific to those processes, methods, articles or apparatus / devices.

[0097] Although the technical proposals of the present invention have been described above in relation to preferred embodiments shown in the drawings, it goes without saying that the scope of protection of the present invention is not limited to these specific embodiments, as will be readily apparent to those skilled in the art. Those skilled in the art can make equivalent modifications or substitutions to the relevant technical features without departing from the principles of the present invention, and all such modified or substituted technical proposals will fall within the scope of protection of the present invention.

Claims

1. An automatic lighting generation method based on airport regulations AIP and satellite image analysis, Step S10 involves analyzing the airport AIP document to extract geometric topology information of the runway and taxiway, including at least the runway endpoint, runway centerline, pavement width, magnetic azimuth angle, and approach light type identifier. Step S20 involves acquiring satellite remote sensing images corresponding to the positions of runways and taxiways, extracting an image boundary point group of runways and taxiways as a set of outline coordinates of features, which are groups of feature boundary points extracted from the satellite remote sensing images, determining whether the deviation between the principal axis direction of the image boundary point group and the magnetic azimuth angle exceeds a preset angular threshold, proceeding to step S30 to execute a ruling strategy if it exceeds the threshold, and proceeding to step S40 if it does not exceed the threshold. Step S30 generates a pavement topology network based on the image boundary point cloud, constructs a dynamic buffer region based on the runway endpoints, maps the nodes within the buffer region to the pavement region defined in the airport AIP document, maintains the original topology for nodes outside the buffer region, outputs a fused pavement spatial reference network, and proceeds to step S50. Step S40 involves directly aligning the image boundary point cloud with the coordinate system where the geometric topology information is located, outputting a fused pavement surface spatial reference network, and proceeding to step S50. Step S50 involves installing lighting nodes in straight sections within the pavement surface spatial reference network based on a preset interval threshold, and installing lighting nodes in curved sections within the pavement surface spatial reference network based on the radius of curvature of the curved sections. Step S60 involves associating lighting attributes with lighting nodes corresponding to different pavement surfaces based on a standard rule library, activating the lighting nodes according to the rule set corresponding to the requirements of the airport operation mode and flight simulation training scenario, and generating airport lighting configuration data to drive the flight simulator viewing system. Includes, The aforementioned arbitrage strategy specifically states: The steps include: constructing a triangulation network according to the image boundary point cloud; removing connected edges from the triangulation network whose deviation in the perpendicular angle with respect to the runway direction exceeds a predetermined threshold; extracting the maximum connected region of the remaining triangulation network; and identifying nodes associated with geometric topology information within the maximum connected region as key nodes. The process involves generating a circular buffer region with a dynamic radius centered on the runway endpoint, mapping key nodes within the buffer region to a reference pavement surface defined in the airport AIP document, and maintaining the original spatial coordinates for key nodes outside the buffer region. The steps include: fusing the mapped nodes with the original nodes to generate a calibrated pavement surface spatial reference network; including, An automatic lighting generation method based on airport regulations AIP and satellite image analysis, characterized by the above.

2. The steps of acquiring satellite remote sensing images corresponding to the locations of runways and taxiways, and extracting image boundary point groups of runways and taxiways as a set of outline coordinates of features, which are groups of feature boundary points extracted from satellite remote sensing images, are specifically as follows: The steps include: segmenting the aforementioned satellite remote sensing image into cloud layers and vegetation-obscuring regions using a convolutional neural network; geometrically correcting the segmented satellite remote sensing image based on a pre-constructed digital elevation model of runways and taxiways; and extracting the image boundary point cloud of the geometrically corrected satellite remote sensing image. including, The method for generating automatic lighting based on airport regulations AIP and satellite image analysis as described in feature 1.

3. A method for calculating the principal axis direction of an image boundary point cloud is: The steps include: calculating a covariance matrix for the image boundary point cloud, determining the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, using the eigenvector corresponding to the largest eigenvalue as the principal axis direction vector, calculating the principal axis azimuth angle based on the principal axis direction vector, and setting this as the principal axis direction of the image boundary point cloud; including, The method for generating automatic lighting based on airport regulations AIP and satellite image analysis as described in feature 1.

4. A method for directly aligning an image boundary point cloud to a coordinate system where geometric topology information is located and outputting a fused pavement surface spatial reference network is: The steps include performing an affine transformation on the image boundary point cloud and superimposing the principal axis direction of the image boundary point cloud onto the magnetic azimuth angle, The process involves performing least-squares fitting based on the runway center point, translating the image boundary point cloud after affine transformation to the pavement area defined in the airport AIP document, and maintaining the topological connection relationships of the transformed image boundary point cloud invariantly. including, The method for generating automatic lighting based on airport regulations AIP and satellite image analysis as described in feature 1.

5. The step of installing lighting nodes in a straight section based on a predetermined interval threshold is, specifically, The steps include: extracting a set of centerlines for all straight sections from the pavement surface spatial reference network, calculating the actual length for each centerline of a straight section, and determining the extension direction vector; The process involves calculating a sequence of lamp node positions according to the principle of equal spacing along the extension direction of a straight section, based on a pre-set interval threshold, and generating an initial set of straight section lamp nodes that includes all straight section lamp nodes. The steps include outputting the initial set of linear light nodes to the light topology network generation module, including, The method for generating automatic lighting based on airport regulations AIP and satellite image analysis as described in feature 1.

6. The step of installing lighting nodes in a curved section based on the radius of curvature is, specifically, The process involves extracting the centerline set and corresponding radius of curvature attribute values ​​for all curved sections from the pavement surface spatial reference network, calculating a dynamic node density adjustment coefficient according to the radius of curvature value of each curved section, and determining that the node density increases as the radius of curvature decreases. The steps include determining the adaptive node interval value of the curve section based on a pre-set interval threshold and a dynamic node density adjustment coefficient, The steps include generating a curved light node position sequence according to adaptive node spacing values ​​along the curved centerline, The steps include generating and outputting a set of curved light nodes that include all curved section light nodes, including, The method for generating automatic lighting based on airport regulations AIP and satellite image analysis as described in feature 5.

7. The process further includes a step of generating intersection nodes, wherein the intersection node generation step is: The steps include: integrating the initial set of straight light nodes and the set of curved light nodes to form a base set of light nodes, and performing triangular mesh division on the intersection area within the pavement surface spatial reference network based on its boundary nodes; The steps include: extracting all vertices generated by triangular mesh division as a set of intersecting ignition nodes, and merging the base ignition node set with the intersecting ignition node set to generate a complete ignition topology network; The steps include outputting the complete lighting topology network to the dynamic rule engine module, including, The method for generating automatic lighting based on airport regulations AIP and satellite image analysis as described in feature 6.

8. The step of associating lighting attributes with lighting nodes corresponding to different pavement surfaces is: The steps include loading a standard rule library, creating an airport rule database that includes a daytime mode rule set, a nighttime mode rule set, and a special situation mode rule set, and the special situation mode rule set includes at least a predefined emergency situation, The steps include classifying and associating lighting nodes within the pavement surface spatial reference network into runway section node sets, taxiway section node sets, and intersection node sets, For each set of nodes in a classification, a corresponding lighting attribute template is constructed, and the lighting attribute template includes color attributes, flashing frequency attributes, and brightness level attributes. The steps include: outputting the attribute-defined light node database to the rule activation module, including, The method for generating automatic lighting based on airport regulations AIP and satellite image analysis as described in feature 1.

9. The steps of activating lighting nodes according to a rule set corresponding to the requirements of the airport operation mode and flight simulation training scenario, and generating airport lighting configuration data to drive the flight simulator viewing system, specifically include: The steps include receiving an airport operation mode command and matching it with the corresponding rule set in the airport rule database, The process involves detecting attribute conflict nodes based on a rule conflict resolver, generating a list of conflict nodes, performing priority determination on the list of conflict nodes, and outputting a conflict resolution decision table. The steps include: activating lighting node attributes according to a conflict resolution decision table and generating airport lighting configuration data to drive the flight simulator view system; including, The method for generating automatic lighting based on airport regulations AIP and satellite image analysis as described in feature 8.

Images