Automatic light generation method based on airport regulation AIP and satellite interpretation

Abstract

This invention belongs to the field of airport lighting generation and control, specifically involving an automatic lighting generation method based on airport access point information (AIP) and satellite image analysis. It aims to solve the problems of high workload, low efficiency, error-proneness, and difficulty in guaranteeing accuracy in airport lighting modeling. The invention includes: parsing AIP documents to extract the geometric topology information of runways and taxiways; acquiring corresponding satellite images and extracting boundary point sets, determining whether the deviation between their principal axis direction and magnetic azimuth exceeds a threshold; if it exceeds the threshold, generating a pavement network based on the satellite point set, and constructing a dynamic buffer to fuse the AIP benchmark with the runway endpoints as the reference; otherwise, directly aligning the coordinate system; deploying lighting nodes on straight sections at preset intervals and on curved sections based on the radius of curvature; associating lighting attributes to nodes according to a standard rule base, activating nodes based on airport operation modes and simulation training requirements, and generating airport lighting configuration data for the flight simulator visual system. This achieves automated, high-precision lighting generation.

Description

Technical Field

[0001] This invention belongs to the field of airport lighting generation and control, and specifically relates to an automatic lighting generation method based on airport regulations AIP and satellite image analysis. Background Technology

[0002] Airport lighting is the cornerstone of aviation safety and a key to operational efficiency. In complex environments, it provides irreplaceable visual reference for aircraft takeoffs, landings, and ground movements. At night or in low visibility conditions, it provides crucial visual guidance for pilots, ensuring that aircraft are precisely aligned with the runway, land and take off safely, and preventing runway incursions, runway overruns, or deviations from the taxiway.

[0003] In flight training, the simulator's visual system, through high-fidelity reproduction of the lighting system, provides pilots with realistic training scenarios. It supports pilots in repeatedly honing their core operational skills, procedural applications, and emergency handling in complex weather and at night in a zero-risk environment, playing a crucial role in flight simulation training.

[0004] Currently, lighting design relies entirely on manual labor, resulting in a massive workload, as each airport requires the placement of numerous lights. Furthermore, due to the complexity of airport lighting—for example, different lights at varying distances from the runway edge require different colors—manual modeling inevitably leads to errors. This results in under- or over-design, or incorrect color selection. Additionally, because there are standard spacing requirements for lights (e.g., 60 meters from the runway edge), these precise values ​​cannot be guaranteed, compromising accuracy to some extent.

[0005] Based on this, the present invention proposes an automatic lighting generation method based on airport access control (AIP) and satellite image analysis. Summary of the Invention

[0006] To address the aforementioned problems in existing technologies, namely the high workload, low efficiency, error-proneness, and difficulty in guaranteeing accuracy in airport lighting modeling, this invention provides an automatic lighting generation method based on airport access control (AIP) and satellite image analysis. This method includes the following steps:

[0007] Step S10: Parse the airport AIP document to extract the geometric topology information of the runway and taxiway, including at least the runway endpoints, runway centerline, pavement width, magnetic azimuth, and approach light type identifier.

[0008] Step S20: Obtain satellite remote sensing images corresponding to the runway and taxiway locations, extract the image boundary point set, and determine whether the deviation between the principal axis direction of the satellite boundary point set and the magnetic azimuth exceeds a preset angle threshold. If it exceeds the threshold, proceed to step S30 to execute the decision strategy; if it does not exceed the threshold, proceed to step S40.

[0009] Step S30: Generate a pavement topology network based on the satellite boundary point set, construct a dynamic buffer area with the runway endpoint as the reference; map the nodes in the buffer to the AIP reference pavement, maintain the original topology for the nodes outside the buffer, output the fused pavement spatial reference network, and jump to step S50.

[0010] Step S40: Align the satellite boundary point set directly to the coordinate system where the geometric topology information is located, output the fused pavement space reference network, and jump to step S50.

[0011] Step S50: Lighting nodes are set up on straight segments in the pavement space reference network based on a preset interval threshold, and lighting nodes are set up on curved segments based on the radius of curvature of the curved segments in the pavement space reference network.

[0012] Step S60: Based on the standard rule base, the lighting attributes are associated with the lighting nodes corresponding to different pavements. The lighting nodes are activated according to the rule set corresponding to the airport operation mode and flight simulation training scenario requirements, generating airport lighting configuration data for driving the flight simulator visual system.

[0013] Furthermore, the principal axis direction of the satellite boundary point set is calculated as follows:

[0014] Calculate the covariance matrix for the satellite boundary point set, solve for the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, take the eigenvector corresponding to the largest eigenvalue as the principal axis direction vector, and calculate the principal axis azimuth angle based on the principal axis direction vector as the principal axis direction of the satellite boundary point set.

[0015] Furthermore, satellite remote sensing images corresponding to the runway and taxiway locations are acquired, and image boundary point sets are extracted, specifically including:

[0016] The satellite remote sensing image is segmented into cloud and vegetation-covered areas using a convolutional neural network. Based on a pre-constructed digital model of runway and taxiway elevation, the segmented satellite remote sensing image is geometrically corrected, and the image boundary point set of the geometrically corrected satellite remote sensing image is extracted.

[0017] Furthermore, the adjudication strategy is specifically as follows:

[0018] A triangulated network is constructed based on the satellite boundary point set; connecting edges in the triangulated network whose perpendicular angle deviation from the runway direction exceeds a preset threshold are deleted; the maximum connected region of the remaining triangulated network is extracted, and nodes in the maximum connected region that are associated with geometric topology information are identified as key nodes;

[0019] A circular buffer zone with a dynamic radius is generated with the runway endpoint as the center. The key nodes within the buffer zone are mapped to the reference pavement defined in the airport AIP document, while the key nodes outside the buffer zone maintain their original spatial coordinates.

[0020] The mapped nodes are merged with the original nodes to generate a calibrated pavement spatial reference network.

[0021] Furthermore, the satellite boundary point set is directly aligned to the coordinate system containing the geometric topology information, and the fused pavement spatial reference network is output. The method is as follows:

[0022] Perform an affine transformation on the satellite boundary point set so that the principal axis of the satellite boundary point set coincides with the magnetic azimuth.

[0023] Least square fitting is performed with the runway center point as the reference, and the affine transformation satellite boundary point set is translated to the pavement area defined in the airport AIP document, while preserving the topological connectivity of the transformed satellite boundary point set.

[0024] Furthermore, the method of deploying light nodes on straight segments based on a preset interval threshold specifically includes:

[0025] Extract the set of centerlines of all straight segments from the pavement space reference network, calculate the actual length of each straight segment centerline and determine the extension direction vector;

[0026] Based on the preset spacing threshold, the position sequence of the light nodes is calculated along the extension direction of the straight line segment according to the principle of equal distribution, and an initial set of straight line light nodes containing all the light nodes of the straight line segment is generated.

[0027] Output the initial set of linear light nodes to the light topology network generation module.

[0028] Furthermore, the arrangement of lighting nodes based on the radius of curvature of the curve segment specifically includes:

[0029] Extract the set of centerlines of all curve segments and their corresponding curvature radius attribute values ​​from the pavement spatial reference network. Calculate the dynamic node density adjustment coefficient based on the curvature radius value of each curve segment, where a smaller curvature radius results in a higher node density.

[0030] Based on the preset spacing threshold and the dynamic node density adjustment coefficient, the adaptive node spacing value of the curve segment is determined.

[0031] Generate a sequence of curve lighting node positions along the curve centerline using adaptive node spacing values;

[0032] Generate and output a set of curve light nodes that includes all curve segment light nodes.

[0033] Furthermore, it also includes the steps for generating intersection nodes:

[0034] The initial straight-line light node set and the curved light node set are merged to form the basic light node set. For the intersection area in the pavement space reference network, triangular meshing is performed based on its boundary nodes.

[0035] Extract all vertices generated by triangular mesh partitioning as the intersection light node set, and merge the basic light node set with the intersection light node set to generate a complete light topology network;

[0036] Output the complete lighting topology network to the dynamic rule engine module.

[0037] Furthermore, the lighting attributes are associated with the corresponding lighting nodes on different pavements, including:

[0038] Load the standard rule base and establish an airport rule database containing daytime mode rule sets, nighttime mode rule sets, and special situation mode rule sets; wherein, the special situation mode rule sets include at least preset emergency situations;

[0039] Classify and associate the lighting nodes in the pavement space reference network with the runway segment node set, taxiway segment node set, and intersection node set;

[0040] Configure a corresponding light attribute template for each type of node set. The light attribute template includes color attribute, blink frequency attribute, and brightness level attribute.

[0041] Output the database of light nodes with attribute definitions to the rule activation module.

[0042] Furthermore, based on the airport operation mode and the rule set corresponding to the flight simulation training scenario requirements, light nodes are activated to generate airport lighting configuration data for driving the flight simulator's visual system. This specifically includes:

[0043] Receive airport operation mode instructions and match the corresponding rule set from the airport rule database;

[0044] Based on the rule-based conflict resolver, conflict nodes are detected, a list of conflict nodes is generated, priority determination is performed on the list of conflict nodes, and a conflict resolution decision table is output.

[0045] Activate the lighting node attributes according to the conflict resolution decision table to generate airport lighting configuration data for driving the flight simulator visual system.

[0046] The beneficial effects of this invention are:

[0047] (1) By automatically parsing AIP documents and satellite remote sensing images, and automatically deploying light nodes and associating light attributes based on the fused pavement spatial reference network, the method of relying on manual placement of lights has been completely changed, greatly shortening the construction time of airport lighting models and significantly reducing labor costs.

[0048] (2) The system automatically associates light attributes based on a standard rule base, avoiding issues such as color errors and under- or over-placement of lights that may occur when manually judging rules such as distance and color. Light node placement is performed using preset interval thresholds and curvature radius calculations, strictly ensuring the precise compliance with key standards such as the 60-meter spacing of runway edge lights, overcoming the difficulty of achieving high precision through manual measurement and placement. A strategy of fusing AIP geometric information with satellite imagery is adopted, and an angle deviation threshold is set for intelligent adjudication, effectively ensuring a high degree of consistency between the generated light layout and the actual airport pavement spatial reference.

[0049] (3) The final generated airport lighting configuration data is designed specifically for driving the flight simulator visual system and can dynamically activate lighting nodes according to the needs of flight simulation training scenarios (such as specific weather, night, and special situations). This provides pilots with a highly realistic, standardized, and flexibly configurable lighting visual environment in the simulator, directly serving the safe and efficient training of high-risk subjects such as complex weather, night, and special situation handling, and ensuring the authenticity and effectiveness of the training scenarios. Attached Figure Description

[0050] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0051] Figure 1 This is a flowchart illustrating an automatic lighting generation method based on airport access control (AIP) and satellite image analysis according to the present invention. Detailed Implementation

[0052] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0053] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0054] This invention provides an automatic lighting generation method based on airport access control (AIP) and satellite image analysis. The method includes the following steps:

[0055] Step S10: Parse the airport AIP document to extract the geometric topology information of the runway and taxiway, including at least the runway endpoints, runway centerline, pavement width, magnetic azimuth, and approach light type identifier.

[0056] Step S20: Obtain satellite remote sensing images corresponding to the runway and taxiway locations, extract the image boundary point set, and determine whether the deviation between the principal axis direction of the satellite boundary point set and the magnetic azimuth exceeds a preset angle threshold. If it exceeds the threshold, proceed to step S30 to execute the decision strategy; if it does not exceed the threshold, proceed to step S40.

[0057] Step S30: Generate a pavement topology network based on the satellite boundary point set, construct a dynamic buffer area with the runway endpoint as the reference; map the nodes in the buffer to the AIP reference pavement, maintain the original topology for the nodes outside the buffer, output the fused pavement spatial reference network, and jump to step S50.

[0058] Step S40: Align the satellite boundary point set directly to the coordinate system where the geometric topology information is located, output the fused pavement space reference network, and jump to step S50.

[0059] Step S50: Lighting nodes are set up on straight segments in the pavement space reference network based on a preset interval threshold, and lighting nodes are set up on curved segments based on the radius of curvature of the curved segments in the pavement space reference network.

[0060] Step S60: Based on the standard rule base, the lighting attributes are associated with the lighting nodes corresponding to different pavements. The lighting nodes are activated according to the rule set corresponding to the airport operation mode and flight simulation training scenario requirements, generating airport lighting configuration data for driving the flight simulator visual system.

[0061] To more clearly explain the automatic lighting generation method based on airport access control (AIP) and satellite image analysis of this invention, the following will be combined with... Figure 1 The steps in the embodiments of the present invention will be described in detail below.

[0062] An automatic lighting generation method based on airport access control (AIP) and satellite image analysis according to a first embodiment of the present invention includes steps S10-S60, each step of which is described in detail below:

[0063] Step S10: Parse the airport AIP document to extract the geometric topology information of the runway and taxiway, including at least the runway endpoints, runway centerline, pavement width, magnetic azimuth, and approach light type identifier.

[0064] In this embodiment, a specialized document parsing engine is used to process the AIP document. For example, based on an XML parsing library or a specific aviation data parsing API, this engine can identify and read specific data fields or tags in the document that define the geometric features of runways and taxiways. The parsing process needs to accurately identify and extract the following key information:

[0065] Runway endpoints: Accurately obtain the latitude and longitude coordinates or projected coordinates of each runway endpoints, which are the reference points for locating the spatial position and orientation of the runway.

[0066] Runway centerline: Extract the geometric information of the straight line segment connecting the two ends of the runway, or the centerline point list containing the midpoint, to determine the precise direction and length of the runway.

[0067] Pavement width: Extract the design width value of each runway and taxiway. This data is crucial for subsequent calculations of lighting placement (such as the offset of the runway edge lights from the centerline).

[0068] Magnetic azimuth: Extract the magnetic azimuth value for each runway, representing the magnetic north direction of the runway centerline, providing a directional reference for subsequent alignment with satellite images or coordinate system transformation.

[0069] Approach Light Type Identifier: Identify and extract the approach lighting system type code (such as "ALSF-I", "CALVERT", "SSALR", etc.) associated with each end of the runway. This identifier is directly related to the selection of approach lighting configuration rules in subsequent steps.

[0070] The extracted information is organized into a structured geometric topology data model. This model clearly expresses the spatial location (endpoint coordinates), geometry (centerline, width), orientation (magnetic azimuth), and key attributes (approach light type) of runways and taxiways. The output of this step is a structured dataset containing basic information about all runways and taxiways, providing an accurate and aeronautical-compliant baseline geometric framework for subsequent steps (especially fusion with satellite imagery and placement of light nodes).

[0071] Step S20: Obtain satellite remote sensing images corresponding to the runway and taxiway locations, extract the image boundary point set, and determine whether the deviation between the principal axis direction of the satellite boundary point set and the magnetic azimuth exceeds a preset angle threshold. If it exceeds the threshold, proceed to step S30 to execute the decision strategy; if it does not exceed the threshold, proceed to step S40.

[0072] In this embodiment, satellite remote sensing images corresponding to the locations of the runway and taxiway are acquired, and the image boundary point set is extracted, specifically including:

[0073] The satellite remote sensing image is segmented into cloud and vegetation-covered areas using a convolutional neural network. Based on a pre-constructed digital model of runway and taxiway elevation, the segmented satellite remote sensing image is geometrically corrected, and the image boundary point set of the geometrically corrected satellite remote sensing image is extracted.

[0074] Specifically, based on the runway and taxiway location coordinates obtained in step S10, the original satellite remote sensing images of the corresponding areas are retrieved from the satellite image database. To eliminate environmental interference, a pre-trained convolutional neural network (CNN) is used to perform semantic segmentation on the images, automatically identifying and masking occluded areas to ensure that the pavement contour extraction is not disturbed.

[0075] For the segmented satellite images, geometric correction is performed by combining them with pre-constructed digital elevation models of runways and taxiways. These digital elevation models can be constructed based on DEMs generated from LiDAR point clouds, which is existing technology and will not be elaborated here. The geometric correction includes spatial correction based on the alignment of the image geographic coordinates with the elevation model, and calculation of the perspective projection transformation matrix using elevation data based on the collinearity equation principle to eliminate image perspective distortion caused by terrain undulations or sensor tilt angles, generating orthorectified images with geometric accuracy down to the sub-meter level.

[0076] The corrected orthophoto image is used to extract the pavement contour. Specifically, the Canny operator or a depth edge detection model is used to extract the runway / taxiway boundaries, transforming the continuous boundaries into an ordered set of image boundary points. .

[0077] In this embodiment, the principal axis direction of the satellite boundary point set is calculated as follows:

[0078] Calculate the covariance matrix for the satellite boundary point set, solve for the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, take the eigenvector corresponding to the largest eigenvalue as the principal axis direction vector, and calculate the principal axis azimuth angle based on the principal axis direction vector as the principal axis direction of the satellite boundary point set.

[0079] Among them, based on image boundary point set The covariance matrix C is constructed as follows:

[0080] ;in, For coordinate variance, For covariance;

[0081] Perform eigenvalue decomposition on matrix C to obtain eigenvalues. and and the corresponding feature vectors , ; .

[0082] Take the largest eigenvalue Corresponding feature vector As the principal axis direction vector of the boundary point set, according to the direction vector components Calculate the principal axis azimuth angle using the arctangent function. ;in, It is the component of the direction vector along the horizontal axis (X-axis) of the image coordinate system. It is the component of the direction vector along the vertical axis (Y-axis) of the image coordinate system.

[0083] Calculate the principal axis azimuth angle With the preset magnetic azimuth angle absolute deviation The system determines whether the absolute deviation exceeds a preset angle threshold, which is between 0.1° and 2°, and preferably 1° in this embodiment.

[0084] Step S30: Generate a pavement topology network based on the satellite boundary point set, construct a dynamic buffer area with the runway endpoint as the reference; map the nodes in the buffer to the AIP reference pavement, maintain the original topology for the nodes outside the buffer, output the fused pavement spatial reference network, and jump to step S50.

[0085] In this embodiment, the adjudication strategy is specifically as follows:

[0086] A triangulated network is constructed based on the satellite boundary point set; connecting edges in the triangulated network whose perpendicular angle deviation from the runway direction exceeds a preset threshold are deleted; the maximum connected region of the remaining triangulated network is extracted, and nodes in the maximum connected region that are associated with geometric topology information are identified as key nodes;

[0087] A circular buffer zone with a dynamic radius is generated with the runway endpoint as the center. The key nodes within the buffer zone are mapped to the reference pavement defined in the airport AIP document, while the key nodes outside the buffer zone maintain their original spatial coordinates.

[0088] The mapped nodes are merged with the original nodes to generate a calibrated pavement spatial reference network.

[0089] In this embodiment, when step S20 determines that the deviation between the main axis direction of the satellite image and the magnetic azimuth angle of the AIP exceeds the limit, this adjudication strategy is activated, including:

[0090] Obtain the satellite boundary point set extracted in step S20 and the AIP geometric topology information containing runway endpoint coordinates resolved in step S10. Perform constrained Delaunay triangulation on the satellite boundary point set to construct a triangulated mesh network covering the pavement area. In this network, the mesh nodes are boundary points and the connecting edges represent the pavement topology.

[0091] To eliminate the impact of satellite image rotation distortion on the topology, directional filtering is performed, including: calculating edge orientation angles, deleting outlier edges, and extracting the maximum connected component.

[0092] The side direction angle is calculated as follows:

[0093] For each edge in the triangular mesh e i Calculate the angle between it and the direction of the AIP runway centerline. α i As the side direction angle.

[0094] Delete the connecting edges in the triangulated network whose perpendicular angle deviation from the runway direction exceeds a preset threshold. In this embodiment, the preset threshold is preferably 15°. Specifically:

[0095] like A preset threshold is set, i.e., if the edge is not approximately perpendicular to the runway direction, the edge is deleted, and the remaining edges form the largest connected subgraph. The set of nodes in the subgraph is defined as the key nodes, which include at least the runway endpoints and taxiway intersections.

[0096] In this embodiment, a circular buffer zone with dynamically expanding radius is generated, centered on the runway endpoint defined in the AIP document. The buffer zone radius is dynamically set as a multiple of the actual runway width; in this embodiment, it is set to 3 times the pavement width to ensure coverage of critical areas at the runway endpoint. For critical nodes falling within the buffer zone, their spatial coordinates are vertically projected onto the AIP reference pavement (such as the runway centerline or taxiway design centerline); nodes outside the buffer zone retain their original satellite image coordinates, preserving local topological authenticity. This zoning mapping strategy achieves a precise balance between strictly aligning the core area with aviation regulations and preserving measured geographical features in non-core areas.

[0097] The calibrated buffer nodes are spatially fused with the original nodes outside the buffer, and the pavement topology network is reconstructed based on the node connectivity. The output fused pavement spatial reference network inherits the standardization of AIP data and incorporates the real-world features of satellite imagery, forming a high-precision spatial reference framework for lighting deployment. This network directly jumps to step S50, driving the subsequent automated deployment process of lighting nodes.

[0098] In this embodiment, the fused pavement spatial reference network is a vectorized structural model composed of spatial node sets, topological connections, and pavement attribute labels. Its core elements include:

[0099] Calibration nodes: Key points located within the dynamic buffer zone at the runway end (such as runway thresholds and taxiway intersections) whose coordinates are mapped to the reference pavement defined by AIP (such as the runway centerline) via vertical projection to ensure absolute consistency with aviation specifications;

[0100] Original nodes: Nodes outside the buffer that retain the original coordinates of satellite images (such as remote taxiways and apron connection points) to maintain the geometry measured in the field;

[0101] Topological connection edges: Based on the effective connection relationships after triangulation and direction filtering, they accurately represent the connectivity of pavement paths (such as runway-taxiway connections and curve turning paths).

[0102] The calibration nodes of the pavement space reference network are associated with the runway width, magnetic azimuth, and approach light type identifiers resolved by AIP, ensuring that the lighting rule base can accurately call the standard parameters;

[0103] The original nodes carry the pavement material type (asphalt / concrete) and boundary curvature radius extracted from satellite images, supporting adaptive calculation of curve lighting density; all nodes are uniformly expressed in WGS-84 or UTM coordinate system, eliminating benchmark differences across data sources.

[0104] To serve flight simulation training scenarios, the network extends the following functional layers:

[0105] Running status markers: Nodes are dynamically marked with "active / off" status;

[0106] Elevation datum: Integrates digital elevation model (DEM) data to provide a vertical datum for ramp lighting generation;

[0107] Logical partitioning: The system divides the area into runway, taxiway, and apron subnets according to ICAO standards, driving differentiated lighting rule sets.

[0108] Step S40: Align the satellite boundary point set directly to the coordinate system where the geometric topology information is located, output the fused pavement spatial reference network, and jump to step S50, specifically:

[0109] Perform an affine transformation on the satellite boundary point set so that the principal axis of the satellite boundary point set coincides with the magnetic azimuth.

[0110] Least square fitting is performed with the runway center point as the reference, and the affine transformation satellite boundary point set is translated to the pavement area defined in the airport AIP document, while preserving the topological connectivity of the transformed satellite boundary point set.

[0111] In this embodiment, the specific steps of the affine transformation are as follows:

[0112] Construct rotation matrix R Rotate the point set around the center of mass This ensures that the main axis of the satellite image is completely aligned with the magnetic azimuth of the AIP, eliminating directional deviation.

[0113] After completing the orientation calibration, least squares fitting is performed based on the runway geometric center point, which specifically includes:

[0114] Extract the vertex set of the polygon region of the runway pavement defined by AIP. The rotated image boundary point set and Perform point set matching;

[0115] Solve for the translation vector ,make minimize;

[0116] Will The entire structure is shifted by T to achieve spatial alignment with the AIP pavement area.

[0117] During the affine transformation (rotation + translation), the original topological connectivity of the satellite boundary point set is strictly preserved:

[0118] The ratio of the angle and distance between the connecting edges of all adjacent points remains unchanged;

[0119] The geometry of the pavement profile (such as taxiway curvature) is consistent with the original satellite image;

[0120] The output transformed point set is the node coordinates of the fused pavement space reference network.

[0121] The registered satellite boundary point set is then merged with the AIP geometric topology information (runway endpoints, centerlines, etc.):

[0122] Satellite point sets represent the actual boundary shape of the track surface;

[0123] AIP data provides key benchmarks for the runway;

[0124] Generate a fused pavement spatial reference network under a unified coordinate system, and proceed to step S50 to drive the deployment of lighting nodes.

[0125] Step S50: Lighting nodes are set up on straight segments in the pavement space reference network based on a preset interval threshold, and lighting nodes are set up on curved segments based on the radius of curvature of the curved segments in the pavement space reference network.

[0126] In this embodiment, the step of deploying light nodes on the straight line segment based on a preset interval threshold specifically includes:

[0127] Extract the set of centerlines of all straight segments from the pavement space reference network, calculate the actual length of each straight segment centerline and determine the extension direction vector;

[0128] Based on the preset spacing threshold, the position sequence of the light nodes is calculated along the extension direction of the straight line segment according to the principle of equal distribution, and an initial set of straight line light nodes containing all the light nodes of the straight line segment is generated.

[0129] Output the initial set of linear light nodes to the light topology network generation module.

[0130] The actual length is calculated as follows:

[0131] Let the coordinates of the endpoints of the centerline be... and Then the length ;

[0132] The extension direction vector The calculation method is as follows:

[0133] After unitization, it becomes .

[0134] Based on the preset spacing threshold D, light nodes are generated according to the principle of equidistant distribution:

[0135] Number of nodes ;

[0136] Coordinates of the kth node:

[0137] ;in, .

[0138] Generate the initial set of linear light nodes It covers all straight line segments.

[0139] Specifically, the preset spacing threshold D is defined in this embodiment as follows:

[0140] For runway edge lights, taxiway edge lights, and stopway lights, the preset spacing threshold D is set to 60 meters; for taxiway centerline lights, the preset spacing threshold D is set to 15 meters.

[0141] The arrangement of lighting nodes based on the radius of curvature of the curve segment specifically includes:

[0142] Extract the set of centerlines of all curve segments and their corresponding curvature radius attribute values ​​from the pavement spatial reference network. Calculate the dynamic node density adjustment coefficient based on the curvature radius value of each curve segment, where a smaller curvature radius results in a higher node density.

[0143] Based on the preset spacing threshold and the dynamic node density adjustment coefficient, the adaptive node spacing value of the curve segment is determined.

[0144] Generate a sequence of curve lighting node positions along the curve centerline using adaptive node spacing values;

[0145] Generate and output a set of curve light nodes that includes all curve segment light nodes.

[0146] Specifically, the set of centerlines of curve segments and the radius of curvature attribute value R are extracted from the pavement spatial reference network, combined with the reference radius. The dynamic node density adjustment coefficient is calculated. The method is as follows: Where, the smaller R is, The larger the value, the higher the node density.

[0147] Specifically, the adaptive node spacing value for the curve segment is determined based on a preset spacing threshold and a dynamic node density adjustment coefficient. The method is as follows:

[0148] .

[0149] Discretize the centerline of the curve into a series of points. To accumulate arc length Based on the adaptive node spacing value The difference generates a node sequence and outputs a set of curve lighting nodes. .

[0150] In this embodiment, the method of generating intersection nodes is also included:

[0151] The initial straight-line light node set and the curved light node set are merged to form the basic light node set. For the intersection area in the pavement space reference network, triangular meshing is performed based on its boundary nodes.

[0152] Extract all vertices generated by triangular mesh partitioning as the intersection light node set, and merge the basic light node set with the intersection light node set to generate a complete light topology network;

[0153] Output the complete lighting topology network to the dynamic rule engine module.

[0154] In this embodiment, the intersection area is the junction of the runway and taxiway. Regarding the intersection area:

[0155] Extract the intersection boundary node set, perform constrained Delaunay triangulation, and generate a triangular mesh. ;

[0156] Extract all vertices after partitioning ;in, Let be the coordinates of the j-th vertex. This represents the total number of grid vertices.

[0157] The merged node set generates a complete lighting topology network, duplicate nodes are deleted, and topological connections (such as edge relationships in triangular meshes) are preserved.

[0158] Step S60: Based on the standard rule base, the lighting attributes are associated with the lighting nodes corresponding to different pavements. The lighting nodes are activated according to the rule set corresponding to the airport operation mode and flight simulation training scenario requirements, generating airport lighting configuration data for driving the flight simulator visual system.

[0159] The core objective of this step is to assign the correct attributes to the light nodes generated in step S50, and to dynamically activate the corresponding light nodes according to different airport operation modes or training scenario requirements, ultimately generating lighting configuration data that can directly drive the flight simulator's visual system. The specific implementation process is as follows:

[0160] In this embodiment, associating lighting attributes with lighting nodes corresponding to different pavements includes:

[0161] Load the standard rule base and establish an airport rule database containing daytime mode rule sets, nighttime mode rule sets, and special situation mode rule sets; wherein, the special situation mode rule sets include at least preset emergency situations;

[0162] Classify and associate the lighting nodes in the pavement space reference network with the runway segment node set, taxiway segment node set, and intersection node set;

[0163] Configure a corresponding light attribute template for each type of node set. The light attribute template includes color attribute, blink frequency attribute, and brightness level attribute.

[0164] Output the database of light nodes with attribute definitions to the rule activation module.

[0165] The configuration rules for the light attribute template include:

[0166] Associate the runway centerline node with a white constant-brightness light template; associate the runway boundary node with a red constant-brightness light template; associate the taxiway centerline node with a blue flashing light template; associate the intersection guidance node with a yellow variable-direction light template; and write the configured attribute templates into the light node database.

[0167] Specifically, the system first loads the predefined standard rule base ICAO. This rule base contains detailed specifications for airport lighting under various operating conditions. Based on this rule base, the system constructs a structured airport rules database. This database mainly contains three key rule sets: a daytime mode rule set for simulating daytime operations, a nighttime mode rule set for simulating nighttime or low-visibility operations, and a special situation mode rule set for simulating special operating conditions (such as emergencies, low-visibility procedures, etc.).

[0168] Next, the system categorizes all light nodes in the pavement spatial reference network and associates them with different node sets based on their location and function. These sets primarily include runway segment node sets (containing runway edge lights, centerline lights, etc.), taxiway segment node sets (containing taxiway edge lights, centerline lights, etc.), and intersection node sets (containing guide line lights, etc.). For each type of node set, the system configures corresponding light attribute templates. These attribute templates define in detail the visual characteristics that nodes should possess, including but not limited to color attributes (such as red, white, blue, yellow), flashing frequency attributes (such as constant brightness, flashing mode, specific frequency), and brightness level attributes. After completing the attribute configuration, the system outputs a light node database with complete attribute definitions and passes it to the subsequent rule activation module for processing.

[0169] When configuring lighting attribute templates, the system follows specific rule mapping logic. Specifically, nodes located at the runway centerline are associated with a white, constant-brightness light template, representing standard runway centerline light characteristics. Nodes located at runway boundaries are associated with a red, constant-brightness light template, representing standard runway edge light characteristics. For nodes at the taxiway centerline, the system associates them with a blue, flashing light template to conform to the typical marking method of taxiway centerline lights. And for guidance nodes in intersection areas, the system associates them with a yellow, variable-direction light template to simulate the characteristics of indicator lights guiding aircraft turns at intersections. All these configured attribute templates are written into the aforementioned lighting node database.

[0170] In this embodiment, light nodes are activated according to the rule set corresponding to the airport operation mode and flight simulation training scenario requirements, generating airport lighting configuration data for driving the flight simulator visual system. Specifically, this includes:

[0171] Receive airport operation mode instructions and match the corresponding rule set from the airport rule database;

[0172] Based on the rule-based conflict resolver, conflict nodes are detected, a list of conflict nodes is generated, priority determination is performed on the list of conflict nodes, and a conflict resolution decision table is output.

[0173] Activate the lighting node attributes according to the conflict resolution decision table to generate airport lighting configuration data for driving the flight simulator visual system.

[0174] Identify light node areas that trigger multiple rules simultaneously;

[0175] When the red boundary light rule and the white centerline light rule are triggered simultaneously in the runway end area, obtain the actual length value of the node from the runway end.

[0176] If the actual length is ≤600 meters, then mark the node as subject to the red light rule;

[0177] If the actual length is greater than 600 meters, then mark the node as retaining the white light rule;

[0178] Output a list of nodes with conflict markers to the priority determination module.

[0179] When it is necessary to generate lighting configurations for specific scenarios, the system receives airport operation mode instructions from external sources (such as "night mode" or "low visibility emergency mode"). Based on the received instructions, the system matches the corresponding rule set (such as the night mode rule set) from the pre-built airport rule database.

[0180] However, in practical applications, some light nodes may be affected by multiple rules or patterns simultaneously, leading to attribute conflicts (for example, a node at the end of a runway may belong to both the runway edge light area and the centerline light rule area). To resolve these conflicts, the system has a built-in rule conflict resolver. This resolver detects all light nodes with attribute conflicts and generates a detailed list of conflicting nodes.

[0181] For each conflicting node in the list, the system executes priority determination logic. For example, when a node in the runway end area is detected to have triggered both the red boundary light rule (runway edge light) and the white centerline light rule, the system will obtain the actual length value of that node from the runway end. If the actual length value is less than or equal to 600 meters, the node is marked as subject to the red light rule (runway edge light).

[0182] Conversely, if the actual length exceeds 600 meters, the node is marked as retaining the white light rule (runway centerline light). This decision-making logic based on specific location parameters is crucial for conflict resolution. Ultimately, the system outputs a conflict resolution decision table, clearly recording the final attribute rule that should be adopted for each conflict node.

[0183] The system strictly follows the instructions of the conflict resolution decision table to activate 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 based on the selected rule set and the conflict resolution results. After activating the attributes of all nodes, the system generates a formatted airport lighting configuration data set. This data contains the precise spatial location of all lighting nodes and their activated visual attribute information. It is specifically designed to be directly input into and drive the visual system of the flight simulator, thereby accurately and dynamically presenting airport lighting effects that conform to aviation specifications and adapt to the needs of specific training scenarios in the simulated environment.

[0184] This embodiment also includes a three-level fault-tolerant feedback mechanism:

[0185] When the geometric verification detects a deviation in node spacing, the constraint satisfaction algorithm is triggered to regenerate the node distribution and update it to the light node database.

[0186] When semantic-level verification detects abnormal light color, the rule engine logs are traced back and the conflict resolution decision table is corrected.

[0187] When business-level verification identifies blind spots in lighting, a supplementary node is inserted into the lighting node database and the attribute association is re-executed.

[0188] To ensure the high accuracy and robustness of the generated airport lighting configuration data, this embodiment specifically designs and integrates a three-level fault-tolerant feedback mechanism. This mechanism operates throughout the entire process of lighting node generation, attribute association, and configuration data output, providing automated detection, diagnosis, and repair capabilities for potential problems at different levels. Its implementation process is as follows:

[0189] After the lighting nodes are deployed, the system performs a geometrical verification. The core task of this level is to verify the accuracy of the lighting nodes' physical spatial distribution, particularly checking whether the preset key spacing standards (such as the 60-meter spacing between 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 with preset interval thresholds. When a node spacing deviation is detected to exceed the allowable tolerance range (for example, a section of runway edge light nodes is detected to have a spacing of 65 meters instead of the standard 60 meters), the system determines it to be a geometrical error. At this point, the system immediately triggers the built-in constraint satisfaction algorithm. This algorithm, based on the geometric constraints of the pavement spatial reference network (such as the direction of straight sections and the curvature of curves) and the spacing rules that must be met, recalculates and optimizes the distribution of lighting nodes in the problem area, ensuring that the node positions strictly conform to the specifications. The corrected node coordinate data is updated to the lighting node database in real time, replacing the original node data with deviations.

[0190] During the light attribute association and rule activation phase, the system performs semantic-level verification. The core task of this level is to ensure that the visual attributes (color, flashing frequency, brightness) assigned to light nodes logically and semantically conform to aviation lighting specifications, and that the result of rule activation is self-consistent. The system analyzes the activated light node database to identify potential semantic anomalies, such as a red light appearing where a green light should be in the runway threshold area, or a taxiway centerline light being configured to be constantly lit when it should be flashing. When such abnormal light colors or behavior patterns are detected, the system classifies them as semantic-level errors. To diagnose the root cause, the system traces back to the detailed operation logs of the rule engine when processing the node, analyzing whether it is a rule matching error, a conflict resolution decision error, or an attribute template association error. Once the specific cause is located (e.g., the conflict resolution decision table incorrectly marks a node at the end of the runway as subject to the white centerline light rule instead of the correct red edge light rule), the system automatically corrects the corresponding erroneous entry in the conflict resolution decision table or corrects the attribute association rule, and triggers the rule engine to reprocess the affected node to ensure that its final attributes conform to the specification semantics.

[0191] After generating the final lighting configuration data, the system performs operational-level verification. The core task of this level is to verify the integrity and functionality of the lighting system based on the actual operational needs of flight simulation training, ensuring sufficient lighting coverage in all critical pavement areas (especially complex areas such as intersections, rapid exit taxiways, and holding positions) to provide pilots with comprehensive visual guidance. The system analyzes the lighting node distribution map by combining the structure of the pavement spatial reference network, airport operating rules, and the requirements of the simulation training scenario. When areas with insufficient or missing lighting coverage (i.e., "lighting blind spots") are identified, such as the lack of necessary guide lights at the connection between a taxiway and the runway, or insufficient lighting node density at the end of a parking stand guide line, the system determines this as an operational-level defect. To compensate for blind spots, the system intelligently inserts supplementary lighting nodes at the identified blind spot locations based on the pavement network topology and operational rules (such as ICAO Annex 14 standards). The newly inserted nodes are assigned the appropriate initial attribute type for that location (such as yellow guide lights) and added to the lighting node database. Subsequently, the system will re-execute the complete attribute association process (i.e., associating light attributes, matching rule sets, conflict resolution, etc. in step S60) for these newly added nodes to ensure that they are correctly configured and activated like other nodes, ultimately forming airport lighting configuration data without blind spots and with complete functions to meet the needs of high-fidelity flight simulation training.

[0192] Although the steps in the above embodiments are described in the above order, those skilled in the art will understand that in order to achieve the effect of this embodiment, different steps do not need to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple variations are all within the protection scope of this invention.

[0193] A second embodiment of the present invention provides an automatic lighting generation system based on airport access control instructions (AIP) and satellite image analysis, and is based on an automatic lighting generation method based on airport access control instructions (AIP) and satellite image analysis. The system includes:

[0194] The geometric topology information parsing module is configured to parse airport AIP documents to extract the geometric topology information of runways and taxiways, including at least runway endpoints, runway centerlines, pavement width, magnetic azimuth, and approach light type identifiers.

[0195] The deviation judgment module is configured to acquire satellite remote sensing images corresponding to the runway and taxiway positions, extract the image boundary point set, and determine whether the deviation between the principal axis direction of the satellite boundary point set and the magnetic azimuth exceeds a preset angle threshold. If it exceeds the threshold, it will jump to the conflict module to execute the adjudication strategy; if it does not exceed the threshold, it will jump to the non-conflict module.

[0196] The conflict module is configured to generate a pavement topology network based on satellite boundary point sets, construct a dynamic buffer zone with runway endpoints as the reference, map nodes within the buffer zone to the AIP reference pavement, maintain the original topology for nodes outside the buffer zone, output the fused pavement spatial reference network, and jump to the deployment module.

[0197] The non-conflict module is configured to directly align the satellite boundary point set to the coordinate system where the geometric topology information is located, output the fused pavement spatial reference network, and jump to the deployment module;

[0198] The deployment module is configured to deploy lighting nodes on straight segments in the pavement space reference network based on a preset interval threshold, and to deploy lighting nodes on curved segments based on the radius of curvature of the curved segments in the pavement space reference network.

[0199] The attribute configuration module is configured to associate lighting attributes with lighting nodes corresponding to different pavements based on a standard rule base. It activates lighting nodes according to the rule set corresponding to the airport operation mode and flight simulation training scenario requirements, generating airport lighting configuration data for driving the flight simulator visual system.

[0200] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the system described above can be found in the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0201] It should be noted that the automatic lighting generation system based on airport access control (AIP) and satellite image analysis provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiments can be merged into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the various modules or steps and are not considered as an improper limitation of the present invention.

[0202] An electronic device according to a third embodiment of the present invention includes:

[0203] At least one processor; and

[0204] A memory communicatively connected to at least one of the processors; wherein,

[0205] The memory stores instructions that can be executed by the processor to implement the above-described automatic lighting generation method based on airport access control (AIP) and satellite image analysis.

[0206] A fourth embodiment of the present invention provides a computer-readable storage medium storing computer instructions, which are executed by the computer to implement the above-described automatic lighting generation method based on airport access instructions (AIP) and satellite image analysis.

[0207] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the storage device and processing device described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0208] Those skilled in the art will recognize that the modules and method steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. The programs corresponding to the software modules and method steps can be placed in random access memory (RAM), main 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 interchangeability of electronic hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the invention.

[0209] The terms “first”, “second”, etc., are used to distinguish similar objects, not to describe or indicate a specific order or sequence.

[0210] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent in such process, method, article, or apparatus / device.

[0211] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. An automatic lighting generation method based on airport access control (AIP) and satellite image analysis, characterized in that, The method includes the following steps: Step S10: Parse the airport AIP document to extract the geometric topology information of the runway and taxiway, including at least the runway endpoints, runway centerline, pavement width, magnetic azimuth angle and approach light type identifier. Step S20: Obtain satellite remote sensing images corresponding to the runway and taxiway locations, extract the image boundary point set, and determine whether the deviation between the principal axis direction of the satellite boundary point set and the magnetic azimuth exceeds a preset angle threshold. If it exceeds the threshold, proceed to step S30 to execute the decision strategy; if it does not exceed the threshold, proceed to step S40. Step S30: Generate a pavement topology network based on the satellite boundary point set, and construct a dynamic buffer zone with the runway endpoints as the reference. Map the nodes within the buffer to the AIP reference pavement, while maintaining the original topology for the nodes outside the buffer. Output the fused pavement space reference network and proceed to step S50. Step S40: Align the satellite boundary point set directly to the coordinate system where the geometric topology information is located, output the fused pavement space reference network, and jump to step S50. Step S50: Based on a preset interval threshold, light nodes are set up for straight segments in the pavement space reference network, and light nodes are set up for curved segments based on the radius of curvature of the curved segments in the pavement space reference network. Step S60: Based on the standard rule base, the lighting attributes are associated with the lighting nodes corresponding to different pavements. The lighting nodes are activated according to the rule set corresponding to the airport operation mode and flight simulation training scenario requirements, generating airport lighting configuration data for driving the flight simulator visual system.

2. The automatic lighting generation method based on airport access control (AIP) and satellite image analysis according to claim 1, characterized in that, Acquire satellite remote sensing images corresponding to the locations of the runway and taxiway, and extract the image boundary point set, specifically including: The satellite remote sensing image is segmented into cloud and vegetation-covered areas using a convolutional neural network. Based on a pre-constructed digital model of runway and taxiway elevation, the segmented satellite remote sensing image is geometrically corrected, and the image boundary point set of the geometrically corrected satellite remote sensing image is extracted.

3. The automatic lighting generation method based on airport access control (AIP) and satellite image analysis according to claim 1, characterized in that, The principal axis direction of the satellite boundary point set is calculated as follows: Calculate the covariance matrix for the satellite boundary point set, solve for the eigenvalues ​​and corresponding eigenvectors of the covariance matrix, take the eigenvector corresponding to the largest eigenvalue as the principal axis direction vector, and calculate the principal axis azimuth angle based on the principal axis direction vector as the principal axis direction of the satellite boundary point set.

4. The automatic lighting generation method based on airport access control (AIP) and satellite image analysis according to claim 1, characterized in that, The specific adjudication strategy is as follows: A triangulated network is constructed based on the satellite boundary point set; connecting edges in the triangulated network whose perpendicular angle deviation from the runway direction exceeds a preset threshold are deleted; the maximum connected region of the remaining triangulated network is extracted, and nodes in the maximum connected region that are associated with geometric topology information are identified as key nodes; A circular buffer zone with a dynamic radius is generated with the runway endpoint as the center. The key nodes within the buffer zone are mapped to the reference pavement defined in the airport AIP document, while the key nodes outside the buffer zone maintain their original spatial coordinates. The mapped nodes are merged with the original nodes to generate a calibrated pavement spatial reference network.

5. The automatic lighting generation method based on airport access control (AIP) and satellite image analysis according to claim 1, characterized in that, The satellite boundary point set is directly aligned to the coordinate system containing the geometric topology information, and the fused pavement spatial reference network is output. The method is as follows: Perform an affine transformation on the satellite boundary point set so that the principal axis of the satellite boundary point set coincides with the magnetic azimuth. Least square fitting is performed with the runway center point as the reference, and the affine transformation satellite boundary point set is translated to the pavement area defined in the airport AIP document, while preserving the topological connectivity of the transformed satellite boundary point set.

6. The automatic lighting generation method based on airport access instructions (AIP) and satellite image analysis according to claim 1, characterized in that, Light nodes are deployed on straight segments based on a preset interval threshold, specifically including: Extract the set of centerlines of all straight segments from the pavement space reference network, calculate the actual length of each straight segment centerline and determine the extension direction vector; Based on the preset spacing threshold, the position sequence of the light nodes is calculated along the extension direction of the straight line segment according to the principle of equal distribution, and an initial set of straight line light nodes containing all the light nodes of the straight line segment is generated. Output the initial set of linear light nodes to the light topology network generation module.

7. The automatic lighting generation method based on airport access instructions (AIP) and satellite image analysis according to claim 6, characterized in that, The lighting nodes are arranged based on the radius of curvature of the curve segment, specifically including: Extract the set of centerlines of all curve segments and their corresponding curvature radius attribute values ​​from the pavement spatial reference network. Calculate the dynamic node density adjustment coefficient based on the curvature radius value of each curve segment, where a smaller curvature radius results in a higher node density. Based on the preset spacing threshold and the dynamic node density adjustment coefficient, the adaptive node spacing value of the curve segment is determined. Generate a sequence of curve lighting node positions along the curve centerline using adaptive node spacing values; Generate and output a set of curve light nodes that includes all curve segment light nodes.

8. The automatic lighting generation method based on airport access control (AIP) and satellite image analysis according to claim 7, characterized in that, It also includes the steps for generating intersection nodes: The initial straight-line light node set and the curved light node set are merged to form the basic light node set. For the intersection area in the pavement space reference network, triangular meshing is performed based on its boundary nodes. Extract all vertices generated by triangular mesh partitioning as the intersection light node set, and merge the basic light node set with the intersection light node set to generate a complete light topology network; Output the complete lighting topology network to the dynamic rule engine module.

9. The automatic lighting generation method based on airport access control (AIP) and satellite image analysis according to claim 1, characterized in that, Associating lighting attributes with lighting nodes corresponding to different pavements includes: Load the standard rule base and establish an airport rule database containing daytime mode rule sets, nighttime mode rule sets, and special situation mode rule sets; wherein, the special situation mode rule sets include at least preset emergency situations; Classify and associate the lighting nodes in the pavement space reference network with the runway segment node set, taxiway segment node set, and intersection node set; Configure a corresponding light attribute template for each type of node set. The light attribute template includes color attribute, blink frequency attribute, and brightness level attribute. Output the database of light nodes with attribute definitions to the rule activation module.

10. The automatic lighting generation method based on airport access instructions (AIP) and satellite image analysis according to claim 9, characterized in that, Based on the airport operation mode and the rule set corresponding to the flight simulation training scenario requirements, the lighting nodes are activated to generate airport lighting configuration data for driving the flight simulator's visual system. This specifically includes: Receive airport operation mode instructions and match the corresponding rule set from the airport rule database; Based on the rule-based conflict resolver, conflict nodes are detected, a list of conflict nodes is generated, priority determination is performed on the list of conflict nodes, and a conflict resolution decision table is output. Activate the lighting node attributes according to the conflict resolution decision table to generate airport lighting configuration data for driving the flight simulator visual system.

Images