Aircraft positioning method and device
The positioning area image is taken through the aircraft's on-board camera and matched with the support map to determine the position of the aircraft, which solves the problem of GNSS inaccurate positioning in the satellite denial environment and realizes the autonomous and high-precision positioning of the aircraft.
Patent Information
- Application Number
- CN202510108669.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-23
- Publication Date
- 2025-05-23
AI Technical Summary
GNSS is difficult to achieve high-precision positioning of the aircraft in a satellite denial environment.
The aircraft's on-board imaging equipment takes an image of the preset position area and matches it with the prepared support map to find the most similar support sub-map, thereby determining the geographical coordinates of the image and finally determining the position of the aircraft.
The autonomous high-precision positioning of the aircraft is achieved when satellite navigation is interfered with, solving the problem that satellite navigation is difficult to achieve high-precision positioning in satellite denial environments.
Smart Images
Figure CN120027796A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of positioning technology, and more specifically, relates to an aircraft positioning method and device. Background Art
[0002] Aircraft (such as drones, airships, etc.) are not affected by satellite communication confrontation or high-altitude cloud cover, have strong maneuverability, long operating range, fast response speed, low cost, and easy deployment and startup. The situation on the modern battlefield is complex and changing rapidly. The role of advanced reconnaissance and strike technology in modern warfare is becoming increasingly important. Aircraft reconnaissance is currently an effective means of achieving reconnaissance and strike. The number of consumer-grade aircraft, especially low-altitude and slow-speed small aircraft, is also increasing rapidly, and they have performed well in application areas such as monitoring and inspection, crop inspection, post-disaster rescue, aerial photography, and food delivery.
[0003] Generally, an aircraft can obtain its absolute position through the Global Navigation Satellite System (GNSS) or beacons. However, GNSS has difficulty in achieving high-precision positioning of an aircraft in a satellite-denied environment. Summary of the invention
[0004] In view of the defects of the prior art, the purpose of the present application is to provide an aircraft positioning method and device, aiming to solve the problem in the prior art that GNSS is difficult to achieve high-precision positioning of aircraft in a satellite denial environment.
[0005] To achieve the above objectives, in a first aspect, the present application provides an aircraft positioning method, comprising:
[0006] When the aircraft reaches the preset positioning area, taking a first image of the preset positioning area based on an imaging device onboard the aircraft;
[0007] Determine a security sub-map in the security map that has the highest similarity to the first image, and determine the geographic coordinates of the first image based on the geographic coordinates of the security sub-map;
[0008] The position of the aircraft is determined based on the geographic coordinates of the first image.
[0009] In some embodiments, determining the guarantee sub-graph with the highest similarity to the first image in the guarantee graph includes:
[0010] Split the assurance graph into multiple assurance subgraphs;
[0011] A guarantee sub-image among the plurality of guarantee sub-images having the highest similarity to the first image is determined.
[0012] In some embodiments, determining the security sub-image with the highest similarity to the first image among the multiple security sub-images includes:
[0013] Inputting image pairs formed by each guarantee sub-graph and the first image into the target neural network respectively, and obtaining the similarity between each guarantee sub-graph and the first image;
[0014] A guarantee sub-image among the plurality of guarantee sub-images having the highest similarity to the first image is determined.
[0015] In some embodiments, the target neural network is obtained by:
[0016] Inputting the preset image pairs as training samples into the preset neural network for training until the preset neural network converges;
[0017] The preset neural network after convergence is determined as the target neural network.
[0018] In some embodiments, the method of obtaining the guarantee map includes:
[0019] Performing distortion correction processing on the visible light satellite image to obtain a second image;
[0020] Performing scene analysis on the second image to obtain a third image;
[0021] Performing infrared inversion on the third image and the visible light satellite image, and extracting infrared feature maps corresponding to the third image and the visible light satellite image respectively;
[0022] The guarantee map is determined to be composed of common features extracted from the infrared feature map and the visible light image.
[0023] In some embodiments, the first image is the same size as the security map.
[0024] In a second aspect, the present application provides an aircraft positioning device, comprising:
[0025] An image acquisition module, used for capturing an image of the preset positioning area based on an imaging device onboard the aircraft when the aircraft reaches the preset positioning area;
[0026] A coordinate determination module is used to determine the security sub-map in the security map with the highest similarity to the image, and determine the geographic coordinates of the image based on the geographic coordinates of the security sub-map;
[0027] The positioning module is used to determine the position of the aircraft based on the geographic coordinates of the image.
[0028] In a third aspect, the present application provides an electronic device comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the programs stored in the memory are executed, the processor is used to execute the method described in the first aspect or any embodiments of the first aspect.
[0029] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method described in the first aspect or any embodiments of the first aspect.
[0030] In a fifth aspect, the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method described in the first aspect or any embodiments of the first aspect.
[0031] In general, the above technical solutions conceived by this application have the following beneficial effects compared with the prior art:
[0032] The aircraft positioning method and device provided by the present application matches the support map with the first image of the preset positioning area, finds the support sub-map in the support map with the highest similarity to the first image, and determines the geographic coordinates of the first image based on the geographic coordinates of the support sub-map, and finally determines the position of the aircraft based on the geographic coordinates of the first image. When realizing the positioning of the aircraft, the present application does not rely on satellite navigation, solves the problem that satellite navigation is difficult to achieve high-precision positioning of the aircraft in a satellite-denied environment, and realizes autonomous high-precision positioning of the aircraft under satellite-free conditions. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 is a flow chart of an aircraft positioning method provided in an embodiment of the present application;
[0034] Figure 2 It is a schematic diagram of the structure of a twin network provided in an embodiment of the present application;
[0035] Figure 3 It is a schematic diagram of the matching result between the security map and the real-time image provided in the embodiment of the present application;
[0036] Figure 4 It is a schematic diagram of the process of preparing a security map provided in an embodiment of the present application;
[0037] Figure 5 It is a schematic diagram of the overall workflow of the aircraft positioning method provided in the embodiment of the present application;
[0038] Figure 6 is a schematic diagram of the structure of an aircraft positioning device provided in an embodiment of the present application;
[0039] Figure 7 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0040] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0041] The term "and / or" in this article is a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The symbol " / " in this article indicates that the associated objects are in an or relationship, for example, A / B means A or B.
[0042] The terms "first", "second", etc. in the specification and claims herein are used to distinguish different objects rather than to describe a specific order of objects. For example, a first image and a second image are used to distinguish different images rather than to describe a specific order of images.
[0043] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.
[0044] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. For example, multiple security subgraphs refer to two or more security subgraphs, etc.
[0045] In the related technologies, the positioning technology of aircraft (such as drones) relies on communication with satellites, which limits the application value of aircraft in satellite communication confrontation scenarios. This application realizes the matching of the guarantee map with the image of the positioning area taken by the aircraft's onboard imaging equipment through the design knowledge and data-driven downward scene matching technology, so as to ensure the autonomous high-precision positioning of the aircraft under the condition of out-of-satellite. The specific implementation is as follows.
[0046] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application.
[0047] See also Figure 1 , an embodiment of the present application provides an aircraft positioning method, including: step 110, step 120 and step 130.
[0048] Step 110: When the aircraft reaches the preset positioning area, a first image of the preset positioning area is captured using an imaging device onboard the aircraft;
[0049] Step 120 determines the security sub-map in the security map that has the highest similarity to the first image, and determines the geographic coordinates of the first image based on the geographic coordinates of the security sub-map;
[0050] Step 130 determines the position of the aircraft based on the geographic coordinates of the first image.
[0051] In the embodiment of the present application, the aircraft may be a drone, an airship, etc.
[0052] By planning the trajectory of the aircraft, a positioning area is selected based on compatibility, and the positioning area is used as the preset positioning area. Compatibility specifically refers to selecting a suitable positioning method or reference point during the trajectory planning and positioning process, so that the navigation information of the aircraft can be well matched with the actual environment or mission requirements, ensuring the effectiveness and accuracy of the trajectory planning.
[0053] When the aircraft arrives, a real-time image of the preset positioning area is captured by the aircraft's onboard imaging device, and the real-time image is the first image. The imaging device can be a visible light camera, an infrared thermal imaging camera, a multi-spectral camera, etc. There is no direct geographic coordinate information in the first image, or geographic coordinate calibration is required by other means.
[0054] The support map is usually used as a reference image and carries known geographic coordinate information (such as longitude and latitude or projection coordinates). The support map can be a visible light satellite image, an aerial image or a map.
[0055] It should be noted that the above-mentioned support map is stored in the storage device of the aircraft.
[0056] A security sub-graph having the highest similarity to the first image is found from the security graph, and the geographic coordinates of the first image are calibrated according to the geographic coordinates of the security sub-graph to determine the geographic coordinates of the first image. The security sub-graph is obtained by splitting / cutting from the security graph.
[0057] In the embodiment of the present application, the geographical coordinates of the center point of the first image can be found based on the geographical coordinates of the first image, and the geographical coordinates of the center point can be used as the position of the aircraft.
[0058] The aircraft positioning method provided in the embodiment of the present application matches the support map with the first image of the preset positioning area, finds the support sub-map in the support map with the highest similarity to the first image, and determines the geographic coordinates of the first image based on the geographic coordinates of the support sub-map, and finally determines the position of the aircraft based on the geographic coordinates of the first image. When realizing the positioning of the aircraft, the present application does not rely on satellite navigation, solves the problem that satellite navigation is difficult to achieve high-precision positioning of the aircraft in a satellite-denied environment, and realizes autonomous high-precision positioning of the aircraft under satellite-free conditions.
[0059] Further, in some embodiments, determining the guarantee sub-graph in the guarantee graph having the highest similarity to the first image includes:
[0060] Split the assurance graph into multiple assurance subgraphs;
[0061] A guarantee sub-image among the plurality of guarantee sub-images having the highest similarity to the first image is determined.
[0062] In the embodiment of the present application, a grid division method can be used to set a reasonable grid size according to the size of the security map, and the entire security map can be divided into multiple small areas according to the predetermined grid size, and each security sub-map corresponds to a unit of the grid. The grid can be a fixed-size rectangle, a positive direction or an irregular area.
[0063] In the embodiment of the present application, the support map may be divided into a plurality of small areas according to the coordinates of the matching area set by the inertial navigation information and the aircraft planning or according to the dispersion range parameters set by the inertial navigation error range.
[0064] The similarity between each security sub-graph and the first image is calculated, and the security sub-graph with the highest similarity to the first image is determined among the security sub-graphs.
[0065] Further, in some embodiments, determining the securing sub-image among the plurality of securing sub-images having the highest similarity to the first image includes:
[0066] Inputting image pairs formed by each guarantee sub-graph and the first image into the target neural network respectively, and obtaining the similarity between each guarantee sub-graph and the first image;
[0067] A guarantee sub-image among the plurality of guarantee sub-images having the highest similarity to the first image is determined.
[0068] In an embodiment of the present application, each security sub-image is combined with the above-mentioned first image to form an image pair, and each image pair is input into the target neural network respectively, and the similarity between the security sub-image in the image pair and the first image is calculated by the target neural network.
[0069] Among them, the target neural network can be a trained twin network.
[0070] From each of the guarantee sub-graphs, a guarantee sub-graph having the highest similarity to the first image is determined.
[0071] Furthermore, in some embodiments, the target neural network is obtained by:
[0072] Inputting the preset image pairs as training samples into the preset neural network for training until the preset neural network converges;
[0073] The preset neural network after convergence is determined as the target neural network.
[0074] Since there is no ground preparation support map operation in the embodiment of the present application, it is necessary to seek a more robust feature extraction method and complete the feature extraction, feature space mapping and feature matching process on the aircraft. Commonly used methods such as designed image structure feature extraction and gradient histogram feature extraction lack stability and generalization, and cannot be manually corrected, and are difficult to apply to the aircraft positioning method provided in the embodiment of the present application. Based on this, the embodiment of the present application adopts a multi-stream twin network framework driven by knowledge and data collaboration.
[0075] Siamese Net is a type of neural network architecture that contains two or more identical subnetworks. This architecture is widely used in the design of tasks that find similarities or the relationship between two comparable things. The input of the twin network is an image pair, and the output is the similarity of the image pair. It has the ability to automatically learn similarity metrics from data, and can be used to determine whether the image targets are the same. This feature is very suitable for the field of image matching. The deep feature metric extracted by the deep convolutional subnetwork with strong robustness can improve the adaptability to different perspectives, sizes and even morphological changes of the target, and accurately find the target contained in the template image from the image to be matched. In order to further enhance the adaptability of the twin network to the target differences in the template image (in the embodiment of the present application, the guarantee subimage is the template image) and the image to be matched (in the embodiment of the present application, the first image is the image to be matched), a heterogeneous twin network is introduced. Considering the asymmetry of the network branch features and metrics, the first and last layers of the original twin network are heterogeneous, and parameters are no longer shared, so that the network can adapt to a wide range of angle changes, target deformation, occlusion interference, and even differences between different sensor data sources.
[0076] The input of a deep neural network is generally a single image, but the Siamese Net is different. Its input is an image pair, and its output is the similarity of the image pair. Neural networks generally learn the feature expression of objects, while the Siamese Net automatically learns the similarity measurement method from the data, which can be used to determine whether the image targets are the same. Therefore, for sample categories that do not exist in the training samples (in the embodiment of the present application, preset image pairs are used as training samples), the Siamese Net can also perform similarity calculations, which plays a certain role in few-sample learning. The structure of the original Siamese Network is relatively simple, such as Figure 2 shown.
[0077] The original twin network is used as the preset neural network. The left and right paths of the original twin network have the same structure and share the weight W, where F W(X) is the feature mapping function fitted by the twin network, which is used to map the preset image pair X to the target feature space and measure the similarity between the images in the preset image pair in the target feature space.
[0078] G W (X 1 ,X 2 ) is the output of the twin network, representing the image X in the input preset image pair 1 and image X 2 The similarity between W (X 1 ,X 2 )=||F W (X 1 )-F W (X 2 )||, for the same type of samples, G W (X 1 ,X 2 ) is large and close to 1, which means that image X 1 and image X 2 The similarity between them is high. For different types of samples, G W (X 1 ,X 2 ) value is small and close to 0, image X 1 and image X 2 The similarity between them is low.
[0079] When the network is trained, the preset image pair (X 1 ,X 2 ), and the corresponding label y. (X 1 ,X 2 ) are targets of the same category, the label y takes the value of 1, otherwise y takes the value of 0, and the loss function L total The definition is as follows:
[0080]
[0081] L((X 1 ,X 2 ),y) (i) =(1-y)L d (G W (X 1 ,X 2 ) (i) )+yL s (G W (X 1 ,X 2 ) (i) )
[0082] In the formula, L((X 1 ,X2 ),y) (i) represents the loss calculated for the i-th image pair and label, L s Representative (X 1 ,X 2 ) is the loss when the target is of the same category, L d Representative (X 1 ,X 2 ) are the losses when they are different categories of targets.
[0083] Then, when L s is a monotonically increasing function, L d When is a monotonically decreasing function, and both functions are differentiable, and the similarity of the same category image pairs in the feature space is guaranteed to be greater than that of different categories, then the total loss function can be minimized, thereby completing the training of the twin network. The preset neural network after convergence is used as the target neural network.
[0084] The so-called multi-stream twin network framework driven by the collaboration of knowledge and data means that during the training process, the workflow of previous guarantee graph preparation is adopted to prepare a structural feature graph with prior knowledge, and then put it into the twin network together, so that the neural network model can not only learn the matching similarity measurement method from the data, but also receive the guidance of prior knowledge.
[0085] It is worth noting that although a lot of labeled data and computational effort are added during the training process, the actual computational effort during the inference phase is the same as that of the conventional two-stream twin network. If the conventional twin network can meet the real-time requirements during the inference phase, then this method framework can also meet the requirements.
[0086] For the positioning of the aircraft under the condition of satellite separation, the downward scene matching technology is used to build a support map through visible light satellite images, and the geographical positioning result of the aircraft is obtained by matching the support map with the first image, such as Figure 3 shown.
[0087] Furthermore, in some embodiments, the method of obtaining the guarantee map includes:
[0088] Performing distortion correction processing on the visible light satellite image to obtain a second image;
[0089] Performing scene analysis on the second image to obtain a third image;
[0090] Performing infrared inversion on the third image and the visible light satellite image, and extracting infrared feature maps corresponding to the third image and the visible light satellite image respectively;
[0091] The guarantee map is determined to be composed of common features extracted from the infrared feature map and the visible light image.
[0092] In the embodiment of the present application, the preparation process of the above-mentioned security map can be realized by the following steps: distortion correction is performed on the visible light satellite image (completed offline) to form a satellite remote sensing visible light image (referred to as a reference map), and the reference map is the second image. The reference map is used to prepare the security map (completed offline or online), and the prepared security map is stored in the storage device of the aircraft.
[0093] The process of preparing the guarantee map is as follows: Figure 4 As shown in the figure. The material thematic map is obtained by analyzing the scene generated by mutiGen / Terravista on the reference map. According to the material thematic map and the satellite remote sensing visible light image, the infrared inversion algorithm based on the missile-borne infrared imaging physical calculation model is used to generate the target infrared reference map corresponding to the material thematic map and the satellite remote sensing visible light image. By analyzing the imaging mechanism, the common features are extracted from the target infrared reference map and the visible light satellite image to prepare the guarantee map. Then, the real-time image taken by the airborne imaging device (i.e., the airborne infrared real-time image) is registered with the guarantee map, and the position of the aircraft is inferred based on the registration result.
[0094] Further, in some embodiments, the first image has the same size as the guarantee map.
[0095] In the embodiment of the present application, the first image and the security image have the same size.
[0096] In the embodiment of the present application, since there is no support map prepared on the ground, it is necessary to complete the registration of the support map with the real-time image on the aircraft.
[0097] Since the resolution of the support map is only better than 10 meters / pixel, when the aircraft is flying at an altitude of 500 meters, each pixel represents an actual distance of 1.09 meters; when the flight altitude is 800 meters, each pixel represents an actual distance of 1.75 meters; when the flight altitude is 1200 meters, each pixel represents an actual distance of 2.63 meters. Since there is a large difference in resolution between the real-time image and the support map, it is first necessary to match the scale of the collected real-time image and the support map based on the measured flight altitude information of the aircraft, and appropriately reduce the resolution of the real-time image to obtain a support map with the same size as the above-mentioned first image (i.e., the real-time image).
[0098] The embodiment of the present application provides an aircraft positioning method, which solves the problem of inaccurate positioning of the drone itself due to interference with satellite navigation by calculating the position of the aircraft itself (such as longitude and latitude coordinates) through the registration result of the real-time image and the support map. The present application is simple and efficient, with high real-time performance and high accuracy.
[0099] Please see further Figure 5The overall workflow of the aircraft positioning method provided in the embodiment of the present application includes: flight planning; selecting a positioning area based on compatibility; correcting visible light satellite image distortion (completed offline) to form a reference map; using the reference map to prepare a support map (completed offline or online); storing the support map in a storage device in the aircraft; the aircraft arrives at a preset positioning area; extracting features from the real-time image / support map based on a target neural network for correlation matching; obtaining the support sub-map with the highest similarity to the implementation image; obtaining the geographical coordinates of the real-time image based on the geographical coordinates of the support sub-map; and obtaining the position of the aircraft based on the geographical coordinates of the real-time image.
[0100] The aircraft positioning device provided in the present application is described below. The aircraft positioning device described below and the aircraft positioning method described above can be referenced to each other.
[0101] See also Figure 6 An aircraft positioning device provided in an embodiment of the present application includes: an image acquisition module 610, a coordinate determination module 620 and a positioning module 630.
[0102] The image acquisition module 610 is used to capture an image of the preset positioning area based on the aircraft's onboard imaging device when the aircraft reaches the preset positioning area;
[0103] A coordinate determination module 620 is used to determine the security sub-map in the security map with the highest similarity to the image, and determine the geographic coordinates of the image based on the geographic coordinates of the security sub-map;
[0104] The positioning module 630 is used to determine the position of the aircraft according to the geographic coordinates of the image.
[0105] The aircraft positioning device provided in the embodiment of the present application matches the support map with the first image of the preset positioning area, finds the support sub-map in the support map with the highest similarity to the first image, and determines the geographic coordinates of the first image based on the geographic coordinates of the support sub-map, and finally determines the position of the aircraft based on the geographic coordinates of the first image. When realizing the positioning of the aircraft, the present application does not rely on satellite navigation, solves the problem that satellite navigation is difficult to achieve high-precision positioning of the aircraft in a satellite-denied environment, and realizes autonomous high-precision positioning of the aircraft under satellite-free conditions.
[0106] It can be understood that the detailed functional implementation of each of the above-mentioned units / modules can be found in the introduction of the aforementioned method embodiment, and will not be repeated here.
[0107] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.
[0108] Based on the method in the above embodiment, the present application embodiment provides an electronic device, see Figure 7 The electronic device may include: a processor (Processor) 710, a communication interface (CommunicationsInterface) 720, a memory (Memory) 730 and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the method in the above embodiment.
[0109] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.
[0110] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.
[0111] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.
[0112] It is understandable that the processor in the embodiment of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.
[0113] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.
[0114] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.
[0115] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.
[0116] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.
Claims
1. A method for positioning an aircraft, characterized in that: include: When the aircraft reaches the preset positioning area, taking a first image of the preset positioning area based on an imaging device onboard the aircraft; Determine a security sub-map in the security map having the highest similarity to the first image, and determine the geographic coordinates of the first image according to the geographic coordinates of the security sub-map; The position of the aircraft is determined according to the geographic coordinates of the first image.
2. The aircraft positioning method according to claim 1, characterized in that: The step of determining the guarantee subgraph having the highest similarity with the first image in the guarantee graph comprises: Splitting the assurance graph into multiple assurance sub-graphs; Determine a guarantee sub-image among multiple guarantee sub-images that has the highest similarity to the first image.
3. The aircraft positioning method according to claim 2, characterized in that: The step of determining the guarantee sub-graph having the highest similarity with the first image among the plurality of guarantee sub-graphs comprises: Inputting image pairs formed by each guarantee sub-graph and the first image into a target neural network respectively, and obtaining similarities between each guarantee sub-graph and the first image; Determine a guarantee sub-image among multiple guarantee sub-images that has the highest similarity to the first image.
4. The aircraft positioning method according to claim 3, characterized in that: The target neural network is obtained by: Inputting a preset image pair as a training sample into a preset neural network for training until the preset neural network converges; The preset neural network after convergence is determined to be the target neural network.
5. The aircraft positioning method according to any one of claims 1 to 4, characterized in that: Methods for obtaining the security map include: Performing distortion correction processing on the visible light satellite image to obtain a second image; performing scene analysis on the second image to obtain a third image; Performing infrared inversion on the third image and the visible light satellite image to extract infrared feature maps corresponding to the third image and the visible light satellite image respectively; It is determined that the guarantee map is composed of common features extracted from the infrared feature map and the visible light image.
6. The aircraft positioning method according to any one of claims 1 to 4, characterized in that: The first image has the same size as the security map.
7. An aircraft positioning device, characterized in that: include: An image acquisition module, used for capturing an image of a preset positioning area based on an imaging device onboard the aircraft when the aircraft reaches the preset positioning area; A coordinate determination module, used to determine the security sub-map in the security map with the highest similarity to the image, and determine the geographic coordinates of the image based on the geographic coordinates of the security sub-map; A positioning module is used to determine the position of the aircraft according to the geographic coordinates of the image.
8. An electronic device, characterized in that: include: at least one memory for storing a computer program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the aircraft positioning method as described in any one of claims 1-6.
9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program runs on a processor, the processor is enabled to execute the aircraft positioning method according to any one of claims 1 to 6.
10. A computer program product, characterized in that When the computer program product runs on a processor, the processor is enabled to execute the aircraft positioning method according to any one of claims 1 to 6.