A route layout method and system based on remote sensing satellite data

Abstract

The present application provides a route layout method and system based on remote sensing satellite data, which relates to the field of route planning technology, including: identifying obstacles based on acquired remote sensing satellite data; calculating the corrected height of obstacles based on satellite attitude parameters and solar incidence angle; combining DEM data with the corrected height of obstacles to construct a digital surface model containing obstacles, and obtaining an obstacle avoidance route layout strategy through the digital surface model according to the requirements of aerial gravity and magnetic measurements. The present application can solve the technical problem in the prior art that it is difficult to fully cover obstacles on the route due to the traditional method relying on ground surveys and manual experience, resulting in potential safety hazards in route planning. By accurately identifying and avoiding aerial obstacles on the route, remote sensing satellite data and digital surface models are used to automatically layout routes that avoid obstacles, thereby improving the safety of route planning.

Description

Technical Field

[0001] The present application relates to the technical field of route planning, and in particular to a route layout method and system based on remote sensing satellite data. Background Art

[0002] In aerial gravity and magnetic surveying, route layout is a crucial link. Aerial gravity and magnetic surveying is usually used in fields such as geological exploration, resource survey and environmental monitoring, and its accuracy directly affects the reliability and application value of the measurement results. However, the traditional route layout method mainly relies on ground surveys and manual experience, and it is difficult to fully and accurately identify and avoid obstacles on the route, such as towers, windmills, high-voltage lines, etc. First, failure to accurately identify and avoid small or partially obstructed obstacles on the route will lead to risks to the safety of measuring equipment and personnel. Secondly, the traditional route layout method does not make full use of the rich information provided by remote sensing satellite data, resulting in inaccurate route planning, which affects the accuracy of aerial gravity and magnetic measurements.

[0003] In summary, there are technical problems in the prior art that the traditional method relies on ground surveys and manual experience, which makes it difficult to fully cover obstacles on the route, resulting in safety hazards in route planning. Summary of the invention

[0004] The purpose of this application is to provide a route layout method and system based on remote sensing satellite data, so as to solve the technical problem in the prior art that the traditional method relies on ground surveys and manual experience, which makes it difficult to fully cover the obstacles on the route, resulting in safety hazards in route planning.

[0005] In view of the above problems, the present application provides a route layout method and system based on remote sensing satellite data.

[0006] In the first aspect, the present application provides a route layout method based on remote sensing satellite data, which is implemented by a route layout system based on remote sensing satellite data, wherein the route layout method based on remote sensing satellite data includes: according to the acquired remote sensing satellite data, obstacle identification is performed to obtain obstacle image identification data, wherein the obstacles are aerial obstacles such as poles, windmills, and high-voltage lines that have an impact on the route; according to satellite attitude parameters and solar incidence angle, the obstacle image identification data is restored in terms of height and shadow size to obtain obstacle corrected height; DEM data is combined with the obstacle corrected height to construct a digital surface model containing obstacles, and according to the requirements of aerial gravity and magnetic measurements, route planning search is performed through the digital surface model to obtain an obstacle avoidance route layout strategy.

[0007] In the second aspect, the present application also provides a route layout system based on remote sensing satellite data, which is used to execute a route layout method based on remote sensing satellite data as described in the first aspect, wherein the route layout system based on remote sensing satellite data includes: an obstacle identification module, which is used to identify obstacles based on the acquired remote sensing satellite data to obtain obstacle image identification data, wherein the obstacles are aerial obstacles such as poles, windmills, and high-voltage lines that have an impact on the route; an obstacle correction module, which is used to restore the height and shadow size of the obstacle image identification data based on satellite attitude parameters and solar incidence angle to obtain the obstacle corrected height; an obstacle avoidance route layout module, which is used to use DEM data in combination with the obstacle corrected height to construct a digital surface model containing obstacles, and according to the requirements of aerial gravity and magnetic measurements, perform route planning search through the digital surface model to obtain an obstacle avoidance route layout strategy.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] Obstacles are identified based on the acquired remote sensing satellite data to obtain obstacle image identification data, where obstacles are aerial obstacles such as poles, windmills, and high-voltage lines that have an impact on the route; the height and shadow size of the obstacle image identification data are restored based on satellite attitude parameters and the sun's incidence angle to obtain the corrected height of the obstacle; a digital surface model containing obstacles is constructed by combining DEM data with the corrected height of the obstacle, and according to the requirements of aerial gravity and magnetic measurements, a route planning search is performed through the digital surface model to obtain an obstacle avoidance route layout strategy. In other words, by accurately identifying and avoiding aerial obstacles on the route, remote sensing satellite data and digital surface models are used to automatically lay out routes that avoid obstacles, thereby improving the safety of route planning.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 A schematic diagram of a flow chart of a route layout method based on remote sensing satellite data for this application;

[0013] Figure 2 This is a structural schematic diagram of a route layout system based on remote sensing satellite data in this application.

[0014] Description of reference numerals: obstacle identification module 11 , obstacle correction module 12 , obstacle avoidance route layout module 13 . DETAILED DESCRIPTION

[0015] This application provides a route layout method and system based on remote sensing satellite data, which solves the technical problem in the prior art that the traditional method relies on ground surveys and manual experience, making it difficult to fully cover obstacles on the route, resulting in potential safety hazards in route planning. By accurately identifying and avoiding aerial obstacles on the route, using remote sensing satellite data and digital surface models, a route that avoids obstacles is automatically laid out, thereby improving the safety of route planning.

[0016] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0017] For example, please refer to the attached Figure 1 The present application provides a route layout method based on remote sensing satellite data, wherein the route layout method based on remote sensing satellite data is applied to a route layout system based on remote sensing satellite data, and the route layout method based on remote sensing satellite data specifically includes the following steps:

[0018] Step 1: Obstacle identification is performed based on the acquired remote sensing satellite data to obtain obstacle image identification data, where obstacles are aerial obstacles such as poles, windmills, and high-voltage lines that have an impact on the route.

[0019] Specifically, high spatial resolution remote sensing satellites are used to obtain image data. High spatial resolution means that the image contains more detailed ground feature information, which is crucial for identifying small obstacles. Remote sensing satellite images are analyzed through image interpretation technology to identify obstacles such as poles, windmills, and high-voltage lines on the route. Image interpretation includes steps such as image enhancement, feature extraction, and pattern recognition. It is the process of extracting information from remote sensing images, which usually involves the use of computer vision and machine learning technologies. Machine learning is used to establish an obstacle recognition model and fine-tune and optimize the model. The model is trained using a training data set containing obstacle samples such as poles, windmills, and high-voltage lines, and the performance of the model is evaluated using an independent validation data set to ensure that the model has good generalization ability. The preprocessed remote sensing satellite image is input into the trained recognition model, and the model will automatically detect and identify obstacles in the image. The model outputs the location, size, and other relevant information of the obstacle to form obstacle image recognition data. High-resolution remote sensing images and interpretation technology provide detailed environmental information, which helps to optimize route design.

[0020] Step 2: According to the satellite attitude parameters and the solar incidence angle, the height and shadow size of the obstacle image recognition data are restored to obtain the corrected height of the obstacle.

[0021] Specifically, the edge information of obstacles and their shadows is extracted from the obstacle image recognition data. The projection size of the obstacle on the image and the length of the shadow are measured. Satellite attitude parameters include pitch angle, yaw angle, and roll angle, which describe the position and direction of the satellite relative to the earth's surface. The solar incidence angle is the angle between the sun's rays and the normal of the earth's surface, which varies with geographical location and time. The height of the obstacle is calculated using a geometric relationship model. When calculating the height of the obstacle, the influence of the terrain on the shadow length is analyzed, including the ground slope and slope aspect. According to the results of the terrain analysis, the shadow length is corrected to eliminate or reduce the influence of terrain factors on the measurement results. The height of the obstacle is recalculated using the corrected shadow length. Considering the possible errors of the satellite attitude parameters and the solar incidence angle, the calculated obstacle height is used to correct the preliminary recognition height in the obstacle image recognition data. The final obstacle height is the corrected height, which reflects the actual height of the obstacle relative to the earth's surface. Using professional remote sensing image processing software and terrain analysis tools, the accurate height of the obstacle is extracted from the remote sensing image through precise data and complex calculations, providing important information for route planning and safe flight.

[0022] Step 3: Use the DEM data in combination with the corrected height of the obstacle to construct a digital surface model containing the obstacle. According to the requirements of aerial gravity and magnetic measurements, perform route planning and search through the digital surface model to obtain an obstacle avoidance route layout strategy.

[0023] Specifically, the calculated obstacle correction height is combined with the DEM data to construct a digital surface model (DSM) containing obstacles. The DSM includes the surface elevation and the elevation information of the obstacles. According to the requirements of the aerial gravity and magnetic measurement tasks, the flight altitude and measurement accuracy are determined, and the search range, grid size, and obstacle avoidance distance are set. The DSM is divided into multiple grid cells for route planning search. Ensure that the route planning considers the obstacle avoidance distance, flight altitude, and measurement accuracy. Use genetic algorithms, simulated annealing algorithms, or other optimization algorithms to search for the best route that meets the constraints on the DSM. The route planning results obtained from the search are evaluated, and the evaluation indicators may include route length, safety, measurement efficiency, etc. Safety evaluation is particularly important, and it is necessary to ensure that the route avoids all obstacles and meets the minimum avoidance distance requirements. The route planning scheme with the best evaluation result is selected as the obstacle avoidance route layout strategy. The obstacle avoidance route layout strategy ensures the safety of the route and optimizes the efficiency of the measurement task. By accurately identifying and avoiding obstacles on the route, an obstacle avoidance route layout strategy that comprehensively considers terrain, obstacles and measurement requirements is obtained to ensure the safety and efficiency of aerial measurement operations.

[0024] Furthermore, step one of this application includes:

[0025] A pre-trained image recognition model is provided, wherein the image recognition model uses the YOLOv5 model as a framework, constructs training and test data sets through obstacle sample data, and uses machine learning technology to train and test the YOLOv5 model through the training and test data sets to obtain a recognition model, which is used to perform image recognition of obstacles; the remote sensing satellite data is used as input data, and obstacles are recognized in the remote sensing satellite data through the image recognition model, and the recognized obstacle data is located, measured, and labeled as an output result.

[0026] Specifically, a large amount of obstacle sample data is collected, including different types of aerial obstacles such as poles, windmills, and high-voltage lines. The collected sample data is cleaned, annotated, and enhanced to ensure data quality and expand the diversity of the data set. The preprocessed data is divided into a training data set and a test data set. The YOLOv5 model is trained with the training data set using machine learning technology, and then tested with the test data set to evaluate the performance of the model. YOLOv5 is used as the framework of the image recognition model. YOLOv5 is an advanced target detection algorithm and the fifth version of the YOLO (You Only Look Once) series of algorithms. YOLO is an object detection algorithm based on deep learning that can detect and classify objects at the same time. YOLOv5 is known for its high speed and high accuracy and is widely used in the field of computer vision, especially in application scenarios that require real-time detection. The YOLOv5 model is adjusted according to the characteristics of the obstacles, including modifying the network structure and adjusting hyperparameters. The trained model is tested with the test data set to evaluate its accuracy, recall rate, and other indicators for identifying obstacles.

[0027] Remote sensing satellite data includes high-resolution satellite images, which contain various types of obstacles. These are used as input data and fed into a pre-trained image recognition model. The model detects and identifies obstacles in remote sensing satellite data, locates, measures, and annotates the identified obstacles, and generates the final output result. Among them, positioning is to determine the specific position of the obstacle in the image, measurement includes the size or height of the obstacle, and annotation is to facilitate the identification of obstacles such as towers, windmills, and high-voltage lines in subsequent analysis or route planning. By accurately identifying and locating obstacles in the route, risks can be effectively avoided and flight safety can be improved. The measurement and annotation data of obstacles provide detailed information for route planning and help optimize route design.

[0028] Further, step 2 of this application includes:

[0029] According to the obstacle image recognition data, edge data and size information of obstacles and shadows are extracted; according to the edge data and size information of obstacles and shadows, a geometric coordinate model is constructed, a geometric relationship model is established according to the satellite attitude parameters and the solar incidence angle, and the geometric relationship model is fitted to the geometric coordinate model; the geometric relationship model is used to restore the obstacle height and shadow size according to the imaging relationship between the satellite attitude parameters, the solar incidence angle and the obstacles and shadows, so as to obtain the corrected height of the obstacle.

[0030] Furthermore, the present application also includes the following steps:

[0031] According to the satellite attitude parameters and the solar incidence angle, the geometric relationship with the earth's surface is determined, and a geometric relationship model for calculating the obstacle height is established; using the triangulation principle, the obstacle height is calculated according to the shadow length and the geometric relationship model, and the obstacle height is used to correct the obstacle recognition height in the obstacle image recognition data to obtain the obstacle corrected height.

[0032] Furthermore, the present application also includes the following steps:

[0033] DEM data corresponding to the remote sensing image is obtained, the DEM data is analyzed to determine the influence of the terrain on the shadow length, and the measured shadow length is corrected according to the influence of the terrain, wherein the influence of the terrain on the shadow length includes the calculation of the influence of the ground slope and the slope direction.

[0034] Specifically, image processing techniques, such as edge detection algorithms (e.g., Canny edge detector), are used to extract the edges of obstacles and shadows from obstacle image recognition data. Edge detection is a technique in image processing used to identify the boundaries of objects in an image. Analyze the obstacle shadow in the image and extract its size information, which involves measuring the length, width, and direction of the shadow. Use the edge data and size information of the obstacle and its shadow to build a geometric coordinate model that describes the position of the obstacle in three-dimensional space. Analyze the satellite attitude parameters, understand the orbit, attitude, and shape of the earth of the satellite, and determine the position and direction of the satellite in space relative to the earth's surface. Satellite attitude parameters describe the position and direction of the satellite relative to the earth's surface, including pitch angle, yaw angle, and roll angle. Consider the solar incidence angle and establish a geometric relationship between sunlight and the earth's surface. The solar incidence angle is the angle between sunlight and the normal of the earth's surface, which changes with time and location, affecting the length and direction of the obstacle shadow. Combined with the geometric relationship, a geometric relationship model for calculating the height of the obstacle is established.

[0035] When calculating the height of obstacles, the effect of terrain on shadow length should be considered, and DEM data should be used to correct for terrain effects. Obtain digital elevation model (DEM) data corresponding to remote sensing images, which contains elevation information on the earth's surface. Use GIS software or other terrain analysis tools to analyze DEM data and extract terrain parameters such as ground slope and aspect. Slope refers to the degree of inclination of the ground, usually expressed as an angle or percentage. Slope affects the angle of sunlight on the ground, thereby affecting the length of the shadow. On steep slopes, shadows may be longer. Aspect refers to the direction in which the ground is inclined, usually given as an angle with the north direction as a reference. Aspect affects the degree of direct sunlight. For example, a south-facing slope receives more sunlight in the northern hemisphere, so the shadow may be shorter. Determine the effect of terrain characteristics (such as ground slope and aspect) on the length of obstacle shadows, and calculate the expected length of shadows under different terrain conditions.

[0036] The original shadow length measured from the remote sensing image is corrected using the calculated terrain effect, including adding or subtracting the correction value or adjusting the original shadow length through the scale factor. Specifically, the correction factor is determined based on the DEM data analysis results, and the correction factor is applied to the shadow length measured in the remote sensing image to obtain the corrected shadow length. The height of the obstacle is calculated based on the shadow length and the geometric relationship model using the triangulation principle. Triangulation is a method of determining the position of an object by measuring the angle and side length of a triangle. When calculating the obstacle height, the effect of the terrain on the shadow length is considered, and the DEM data is used to correct the terrain effect to ensure the accuracy of the shadow length. The calculated obstacle height is used to correct the preliminary recognition height in the obstacle image recognition data. Considering possible errors, such as the uncertainty of satellite attitude parameters, image resolution limitations, etc., the correction process needs to compensate for these factors. Finally, the corrected height of the obstacle is obtained, taking into account the effect of the terrain on the shadow length, as well as the changes in satellite attitude parameters and the angle of incidence of the sun. By accurately describing the spatial position of the obstacle and its relationship with sunlight, risks can be effectively avoided and flight safety can be improved.

[0037] Further, step three of this application includes:

[0038] The DEM data is preprocessed to ensure the consistency of the DEM data with the remote sensing image and obstacle data, the obstacle correction is highly integrated into the DEM data, and the digital surface model is constructed.

[0039] Furthermore, the present application also includes the following steps:

[0040] According to the requirements of aerial gravity and magnetic measurements, the key parameters of route planning are determined, including flight altitude and measurement accuracy. According to the flight altitude and measurement accuracy, the search range, grid size and obstacle avoidance distance are set. With the search range, grid size and obstacle avoidance distance as constraints, a measurement network is laid out on the digital surface model. With route length, safety and measurement efficiency as evaluation targets, a search is conducted for measurement network layout results to obtain an obstacle avoidance route layout strategy, which is a measurement network layout result with the best evaluation result when the search convergence target is reached.

[0041] Specifically, obtain the digital elevation model (DEM) data corresponding to the remote sensing image, which contains the elevation information of the earth's surface. Preprocess the DEM data to ensure its consistency with the remote sensing image and obstacle data, including data correction, coordinate conversion, resolution matching and other steps. Secondly, if there are DEM data from multiple sources, data fusion is required to create a unified DEM. Remove noise and unreasonable elevation values ​​in the DEM data, and fill in blanks or invalid values ​​in the data. Combine the obstacle corrected height data with the processed DEM data to build a digital surface model (DSM) containing obstacles. DSM is a three-dimensional model that contains the height of the surface and all obstacles on the surface (such as buildings, trees, poles, etc.). Clarify the specific requirements of aerial gravity and magnetic measurement tasks, including the required measurement range, accuracy, coverage area, etc. Select the appropriate flight altitude according to the measurement requirements. The flight altitude will affect the measurement accuracy and coverage. Determine the required measurement accuracy according to the measurement requirements. Measurement accuracy is an important indicator to measure the accuracy of measurement data.

[0042] According to flight altitude, measurement accuracy and other parameters, set the search range, grid size and obstacle avoidance distance. Specifically, define the area range of route planning to ensure that all areas that need to be measured are covered. Determine the spatial grid size used for route planning. The grid size will affect the resolution and calculation amount of route planning. According to the size, shape and flight safety requirements of the obstacles, set the minimum safe distance that the aircraft needs to maintain from the obstacles. According to the constraints of search range, grid size and obstacle avoidance distance, the measurement network is laid out on the digital surface model. The measurement network layout refers to the layout of measurement points or measurement lines in a specific geographical area according to certain rules and requirements to meet specific measurement tasks.

[0043] Taking route length, safety, and measurement efficiency as evaluation targets, optimization algorithms such as genetic algorithms and simulated annealing algorithms are used to search for the best network layout scheme on the DSM. Each network layout scheme is evaluated, considering route length, safety (such as obstacle avoidance), and measurement efficiency. Evaluation indicators may include total route length, minimum distance to obstacles, and integrity of data collection. The network layout scheme with the best evaluation result is selected as the obstacle avoidance route layout strategy. The search convergence target usually means that the algorithm has found one or more optimal solutions that meet all constraints. These solutions are usually network layout schemes that can achieve the best route length, safety, and measurement efficiency within a given search range, grid size, and obstacle avoidance distance. When the search algorithm reaches the convergence target, the network layout result with the best evaluation result is selected as the obstacle avoidance route layout strategy. By automatically laying out obstacle avoidance routes based on the requirements of aerial gravity and magnetic measurements and combining the constructed DSM data containing obstacles, the safety risks in the aerial gravity and magnetic measurement process are effectively reduced.

[0044] In summary, the route layout method based on remote sensing satellite data provided by this application has the following technical effects:

[0045] Obstacles are identified based on the acquired remote sensing satellite data to obtain obstacle image identification data, where obstacles are aerial obstacles such as poles, windmills, and high-voltage lines that have an impact on the route; the height and shadow size of the obstacle image identification data are restored based on satellite attitude parameters and the sun's incidence angle to obtain the corrected height of the obstacle; a digital surface model containing obstacles is constructed by combining DEM data with the corrected height of the obstacle, and according to the requirements of aerial gravity and magnetic measurements, a route planning search is performed through the digital surface model to obtain an obstacle avoidance route layout strategy. In other words, by accurately identifying and avoiding aerial obstacles on the route, remote sensing satellite data and digital surface models are used to automatically lay out routes that avoid obstacles, thereby improving the safety of route planning.

[0046] Embodiment 2: Based on the same inventive concept as the route layout method based on remote sensing satellite data in the above embodiment, the present application also provides a route layout system based on remote sensing satellite data, please refer to the attached Figure 2 , the route layout system based on remote sensing satellite data includes:

[0047] The obstacle recognition module 11 is used to perform obstacle recognition based on the acquired remote sensing satellite data to obtain obstacle image recognition data, wherein the obstacles are aerial obstacles such as poles, windmills, and high-voltage lines that have an impact on the route.

[0048] The obstacle correction module 12 is used to restore the height and shadow size of the obstacle image recognition data according to the satellite attitude parameters and the sun's incidence angle to obtain the obstacle correction height.

[0049] The obstacle avoidance route layout module 13 is used to use the DEM data in combination with the obstacle correction height to construct a digital surface model containing obstacles, and according to the requirements of aerial gravity and magnetic measurements, perform route planning and search through the digital surface model to obtain an obstacle avoidance route layout strategy.

[0050] Furthermore, the obstacle identification module 11 in the route layout system based on remote sensing satellite data is also used for:

[0051] A pre-trained image recognition model is provided, wherein the image recognition model uses the YOLOv5 model as a framework, constructs training and test data sets through obstacle sample data, and uses machine learning technology to train and test the YOLOv5 model through the training and test data sets to obtain a recognition model, which is used to perform image recognition of obstacles; the remote sensing satellite data is used as input data, and obstacles are recognized in the remote sensing satellite data through the image recognition model, and the recognized obstacle data is located, measured, and labeled as an output result.

[0052] Furthermore, the obstacle correction module 12 in the route layout system based on remote sensing satellite data is also used for:

[0053] According to the obstacle image recognition data, edge data and size information of obstacles and shadows are extracted; according to the edge data and size information of obstacles and shadows, a geometric coordinate model is constructed, a geometric relationship model is established according to the satellite attitude parameters and the solar incidence angle, and the geometric relationship model is fitted to the geometric coordinate model; the geometric relationship model is used to restore the obstacle height and shadow size according to the imaging relationship between the satellite attitude parameters, the solar incidence angle and the obstacles and shadows, so as to obtain the corrected height of the obstacle.

[0054] Furthermore, the obstacle correction module 12 in the route layout system based on remote sensing satellite data is also used for:

[0055] According to the satellite attitude parameters and the solar incidence angle, the geometric relationship with the earth's surface is determined, and a geometric relationship model for calculating the obstacle height is established; using the triangulation principle, the obstacle height is calculated according to the shadow length and the geometric relationship model, and the obstacle height is used to correct the obstacle recognition height in the obstacle image recognition data to obtain the obstacle corrected height.

[0056] Furthermore, the obstacle correction module 12 in the route layout system based on remote sensing satellite data is also used for:

[0057] DEM data corresponding to the remote sensing image is obtained, the DEM data is analyzed to determine the influence of the terrain on the shadow length, and the measured shadow length is corrected according to the influence of the terrain, wherein the influence of the terrain on the shadow length includes the calculation of the influence of the ground slope and the slope direction.

[0058] Furthermore, the obstacle avoidance route layout module 13 in the route layout system based on remote sensing satellite data is also used for:

[0059] The DEM data is preprocessed to ensure the consistency of the DEM data with the remote sensing image and obstacle data, the obstacle correction is highly integrated into the DEM data, and the digital surface model is constructed.

[0060] Furthermore, the obstacle avoidance route layout module 13 in the route layout system based on remote sensing satellite data is also used for:

[0061] According to the requirements of aerial gravity and magnetic measurements, the key parameters of route planning are determined, including flight altitude and measurement accuracy. According to the flight altitude and measurement accuracy, the search range, grid size and obstacle avoidance distance are set. With the search range, grid size and obstacle avoidance distance as constraints, a measurement network is laid out on the digital surface model. With route length, safety and measurement efficiency as evaluation targets, a search is conducted for measurement network layout results to obtain an obstacle avoidance route layout strategy, which is a measurement network layout result with the best evaluation result when the search convergence target is reached.

[0062] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The route layout method based on remote sensing satellite data and the specific examples in the first embodiment are also applicable to the route layout system based on remote sensing satellite data in the present embodiment. Through the above detailed description of the route layout method based on remote sensing satellite data, those skilled in the art can clearly know the route layout system based on remote sensing satellite data in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0063] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0064] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A route layout method based on remote sensing satellite data, characterized in that: The route layout method based on remote sensing satellite data includes: Obstacle identification is performed based on the acquired remote sensing satellite data to obtain obstacle image identification data, where obstacles are aerial obstacles such as poles, windmills, and high-voltage lines that have an impact on the route; According to the satellite attitude parameters and the solar incidence angle, the height and shadow size of the obstacle image recognition data are restored to obtain the corrected height of the obstacle; The DEM data is combined with the obstacle correction height to construct a digital surface model containing obstacles. According to the requirements of aerial gravity and magnetic measurements, the route planning search is carried out through the digital surface model to obtain the obstacle avoidance route layout strategy; The obstacle identification is performed based on the acquired remote sensing satellite data, including: A pre-trained image recognition model, wherein the image recognition model uses the YOLOv5 model as a framework, constructs training and test data sets through obstacle sample data, and uses machine learning technology to train and test the YOLOv5 model through the training and test data sets to obtain a recognition model for image recognition of obstacles; The remote sensing satellite data is used as input data, obstacles are identified in the remote sensing satellite data through the image recognition model, and the identified obstacle data is located, measured and marked as output results.

2. A route layout method based on remote sensing satellite data as claimed in claim 1, characterized in that: The step of restoring the height and shadow size of the obstacle image recognition data according to the satellite attitude parameters and the solar incidence angle to obtain the obstacle correction height includes: Extracting edge data and size information of obstacles and shadows according to the obstacle image recognition data; Constructing a geometric coordinate model according to the edge data and size information of the obstacles and shadows, establishing a geometric relationship model according to the satellite attitude parameters and the sun incidence angle, and fitting the geometric relationship model to the geometric coordinate model; The geometric relationship model is used to restore the obstacle height and shadow size according to the imaging relationship between satellite attitude parameters, solar incidence angle, obstacles and shadows, and obtain the obstacle corrected height.

3. A route layout method based on remote sensing satellite data as claimed in claim 2, characterized in that: The geometric relationship model is used to restore the obstacle height and shadow size according to the imaging relationship between the satellite attitude parameters, the solar incidence angle, the obstacles and the shadows, and obtain the obstacle correction height, including: Determine the geometric relationship with the earth's surface based on the satellite attitude parameters and the sun's incidence angle, and establish a geometric relationship model for calculating the obstacle height; The obstacle height is calculated according to the shadow length and the geometric relationship model using the triangulation principle, and the obstacle recognition height in the obstacle image recognition data is corrected using the obstacle height to obtain the obstacle correction height.

4. A route layout method based on remote sensing satellite data as claimed in claim 3, characterized in that: The method uses the triangulation principle to calculate the obstacle height according to the shadow length and the geometric relationship model, and also includes: DEM data corresponding to the remote sensing image is obtained, the DEM data is analyzed to determine the influence of the terrain on the shadow length, and the measured shadow length is corrected according to the influence of the terrain, wherein the influence of the terrain on the shadow length includes the calculation of the influence of the ground slope and the slope direction.

5. The route layout method based on remote sensing satellite data according to claim 1, characterized in that: The DEM data is combined with the obstacle correction height to construct a digital surface model including obstacles, including: The DEM data is preprocessed to ensure the consistency of the DEM data with the remote sensing image and obstacle data, the obstacle correction is highly integrated into the DEM data, and the digital surface model is constructed.

6. A route layout method based on remote sensing satellite data as claimed in claim 5, characterized in that: According to the requirements of aerial gravity and magnetic measurement, the route planning search is performed through the digital surface model to obtain the obstacle avoidance route layout strategy, including: Determine the key parameters of route planning, including flight altitude and measurement accuracy, based on the requirements of aerial gravity and magnetic measurements; According to the flight altitude and measurement accuracy, the search range, grid size and obstacle avoidance distance are set, and the search range, grid size and obstacle avoidance distance are used as constraints. A measurement network is laid out on the digital surface model, and the route length, safety and measurement efficiency are used as evaluation targets. The measurement network layout results are searched to obtain an obstacle avoidance route layout strategy, which is a measurement network layout result with the best evaluation result when the search convergence target is reached.

7. A route layout system based on remote sensing satellite data, characterized in that: Steps for implementing a method for route layout based on remote sensing satellite data as described in any one of claims 1 to 6, wherein the route layout system based on remote sensing satellite data comprises: An obstacle recognition module, which is used to perform obstacle recognition based on the acquired remote sensing satellite data to obtain obstacle image recognition data, wherein the obstacles are aerial obstacles such as poles, windmills, and high-voltage lines that have an impact on the route; An obstacle correction module, which is used to restore the height and shadow size of the obstacle image recognition data according to the satellite attitude parameters and the sun incidence angle to obtain the obstacle correction height; An obstacle avoidance route layout module, which is used to combine the DEM data with the obstacle correction height to construct a digital surface model containing obstacles, and to perform route planning and search through the digital surface model according to the requirements of aerial gravity and magnetic measurements to obtain an obstacle avoidance route layout strategy; The obstacle recognition module is also used for: A pre-trained image recognition model is provided, wherein the image recognition model uses the YOLOv5 model as a framework, constructs training and test data sets through obstacle sample data, and uses machine learning technology to train and test the YOLOv5 model through the training and test data sets to obtain a recognition model, which is used to perform image recognition of obstacles; the remote sensing satellite data is used as input data, and obstacles are recognized in the remote sensing satellite data through the image recognition model, and the recognized obstacle data is located, measured, and labeled as an output result.

Images