Satellite image-based target reconstruction method, device, equipment and medium

Abstract

The application provides a target reconstruction method and device based on satellite images, equipment and medium, comprising: determining a target in the satellite image based on the satellite image; matching the target with three-dimensional models in a target model library to determine a three-dimensional model matched with the target as a target model; determining a three-dimensional simulation scene based on the target model; and generating a strike target matched with a battlefield situation based on the three-dimensional simulation scene. The application is used to solve the problem that users need to manually identify strike targets in the prior art, and the identification efficiency of strike targets is low, and the identification efficiency of strike targets is improved.

Description

Technical Field

[0001] This invention relates to the field of image recognition technology, and in particular to a target reconstruction method, apparatus, device, and medium based on satellite images. Background Technology

[0002] Image recognition technology is an important field of artificial intelligence, with wide applications in military and criminal investigation. With the development of image recognition technology, it is increasingly being used in the construction of 3D scenes.

[0003] In existing technologies, on the battlefield, users need to manually identify battlefield targets, which results in low target identification efficiency. Summary of the Invention

[0004] This invention provides a target reconstruction method, apparatus, device, and medium based on satellite imagery, which addresses the shortcomings of existing technologies where users need to manually identify battlefield targets, resulting in low target identification efficiency, and improves the efficiency of target identification.

[0005] This invention provides a target reconstruction method based on satellite imagery, comprising:

[0006] Based on satellite imagery, the target in the satellite imagery is determined;

[0007] The target is matched with three-dimensional models in the target model library, and the three-dimensional model that matches the target is determined as the target model;

[0008] Based on the target model, a three-dimensional simulation scene is determined;

[0009] Based on the aforementioned 3D simulation scenario, strike targets matching the battlefield conditions are generated.

[0010] According to a target reconstruction method based on satellite imagery provided by the present invention, the target is matched with three-dimensional models in a target model library to determine the three-dimensional model that matches the target as the target model, including:

[0011] Based on satellite imagery, the characteristic information of the target is determined;

[0012] Based on the feature information, the target is matched with three-dimensional models in the target model library, and the three-dimensional model that matches the target is determined as the target model.

[0013] According to the present invention, a target reconstruction method based on satellite imagery is provided, which determines the feature information of the target based on satellite imagery, including:

[0014] Import the satellite images into the battlefield situation map;

[0015] The satellite imagery is adjusted to match the battlefield situation map.

[0016] Based on the adjusted satellite image, the feature information of the target is determined.

[0017] According to a target reconstruction method based on satellite imagery provided by the present invention, the feature information of the target includes the target's location information, quantity information, and type information;

[0018] The location information includes the area of ​​the region where the target is located, the proportion of each small target in the region, and the geographical information of the target.

[0019] The quantity information includes the sum of all targets displayed in the satellite image;

[0020] The category information includes the classification results of the target according to different item types.

[0021] According to the present invention, a target reconstruction method based on satellite imagery is provided, which determines targets in the satellite imagery based on the satellite imagery, including:

[0022] The satellite image is identified using satellite image recognition technology to determine the target within the satellite image.

[0023] According to a target reconstruction method based on satellite imagery provided by the present invention, after generating strike targets that match the battlefield conditions based on the three-dimensional simulation scene, the method includes:

[0024] Based on the aforementioned three-dimensional simulation scenario, the equivalent damage trees of both enemy and friendly targets are determined;

[0025] Based on the three-dimensional simulation scene and the equivalent damage tree, the equivalent damage criteria for both enemy and friendly targets are determined.

[0026] The present invention also provides a target reconstruction apparatus based on satellite imagery, comprising:

[0027] The target recognition module is used to determine targets in the satellite images based on satellite images;

[0028] The model matching module is used to match the target with the three-dimensional models in the target model library, and determine the three-dimensional model that matches the target as the target model;

[0029] The simulation module is used to determine a three-dimensional simulation scene based on the target model;

[0030] The target generation module is used to generate targets that match the battlefield conditions based on the three-dimensional simulation scene.

[0031] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the target reconstruction method based on satellite imagery as described above.

[0032] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the target reconstruction method based on satellite imagery as described above.

[0033] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the target reconstruction method based on satellite imagery as described above.

[0034] The present invention provides a target reconstruction method, apparatus, device, and medium based on satellite images. By identifying targets in satellite images and matching them with a large number of 3D models in a target model library, a matching 3D model is obtained as the target model. Then, a 3D simulation scene is constructed based on the matching model. This enables the identification of strike targets that match the battlefield conditions based on the battlefield environment constructed in the 3D simulation scene, achieving rapid target reconstruction. Furthermore, based on the reconstructed 3D simulation scene, the battlefield conditions and strike targets that match the battlefield conditions are quickly identified, eliminating the need for manual identification of battlefield strike targets, thus improving the efficiency and accuracy of strike target identification. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0036] Figure 1 This is one of the flowcharts illustrating the target reconstruction method based on satellite imagery provided by the present invention;

[0037] Figure 2 This is the second flowchart illustrating the target reconstruction method based on satellite imagery provided by the present invention;

[0038] Figure 3 This is the third flowchart illustrating the target reconstruction method based on satellite imagery provided by this invention;

[0039] Figure 4 This is the fourth flowchart illustrating the target reconstruction method based on satellite imagery provided by this invention;

[0040] Figure 5This is a schematic diagram of the target reconstruction device based on satellite images provided by the present invention;

[0041] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0043] The following is combined with Figures 1-4 The present invention describes a target reconstruction method based on satellite imagery.

[0044] Please refer to Figure 1 The target reconstruction method based on satellite imagery proposed in this invention includes:

[0045] Step 10: Based on satellite imagery, identify the targets in the satellite imagery;

[0046] Targets are generally divided into single targets and cluster targets. A single target is an independent entity, while a cluster target is a group of targets composed of independent entities. Targets can be either single targets or cluster targets composed of independent entities. For example, targets can include buildings, vehicles, green spaces, airports, equipment, roads, houses, hospitals, banks, etc.

[0047] Acquiring satellite imagery of the battlefield environment involves obtaining both the battlefield itself and targets within it. This imagery can be acquired using advanced reconnaissance technologies such as drones, aerial photography, and satellites. Satellite sensors capture data reflecting surface features, which is then processed using specialized remote sensing techniques to produce high-precision satellite images. After obtaining the satellite imagery of the battlefield environment, target identification techniques, including image recognition, machine learning, and human intervention, are used to identify targets and their location, quantity, and type.

[0048] Currently, there are generally two methods for acquiring satellite images of the ground: The first is to use a camera to take photographic images. The camera, loaded with the film, is placed on a satellite, which is then sent into a designed orbit to photograph the ground. After the photography is complete, the satellite is retrieved, and the film is processed through a series of photographic steps. This film can then be digitized by scanning, resulting in digital satellite images. The second method is "digital imaging," whose imaging principle is similar to that of a digital camera.

[0049] Step 20: Match the target with the three-dimensional models in the target model library, and determine the three-dimensional model that matches the target as the target model;

[0050] After target identification, analysis and comparison are performed on the 3D models from the target model library. A large number of 3D models are pre-imported from this library; these models can be pre-built within the 3D system or imported from existing models. The library contains a vast number of 3D models that can be automatically associated and matched with content identified through satellite image recognition technology to find the 3D model that matches the target, thus rapidly reconstructing the entire battlefield environment.

[0051] Step 30: Based on the target model, determine the three-dimensional simulation scene;

[0052] Based on the identified image information and existing target models, the system automatically and rapidly reconstructs battlefield targets, building a 3D simulation scene that includes the battlefield environment and the targets within it. The target models are first scaled or enlarged proportionally and then combined according to the battlefield environment shown in the satellite imagery to obtain the 3D simulation scene. This 3D simulation scene includes both the battlefield environment and the targets within it. It should be noted that the battlefield environment and targets in the 3D simulation scene correspond to the battlefield environment shown in the satellite imagery. By constructing a 3D simulation scene of the battlefield environment and targets, battlefield environment visualization is achieved, enhancing commanders' understanding of the battlefield.

[0053] Based on information such as the target area, target type, and location, the target model is imported to construct a three-dimensional simulation scene.

[0054] Step 40: Based on the three-dimensional simulation scene, generate strike targets that match the battlefield conditions.

[0055] After constructing a 3D simulation scene containing the battlefield environment and targets within it, the system rapidly identifies targets within the 3D simulation scene based on the input strike information, directly and quickly generating strike targets that match the battlefield conditions. For example, assuming the target is a base in the battlefield environment, the 3D simulation scene is identified, the base is identified, and the base is selected as the strike target. The target reconstruction method based on satellite imagery provided by this invention can achieve rapid target reconstruction and battlefield environment construction. It not only enables rapid generation of strike targets from the constructed 3D simulation scene with high feasibility but also provides insights for other target reconstruction fields.

[0056] The target reconstruction method based on satellite imagery provided by this invention identifies targets in satellite images and matches them with a large number of 3D models in a target model library to obtain a 3D model that matches the target as the target model. Then, a 3D simulation scene is constructed based on the model that matches the target, thereby enabling the identification of strike targets that match the battlefield conditions based on the battlefield environment constructed in the 3D simulation scene. This achieves rapid target reconstruction, and based on the reconstructed 3D simulation scene, the battlefield conditions and strike targets that match the battlefield conditions are quickly identified without the need for manual identification of battlefield strike targets, thus improving the efficiency and accuracy of strike target identification.

[0057] In one embodiment, please refer to Figure 2 Step 20 involves matching the target with 3D models in the target model library to determine the 3D model that matches the target as the target model, including:

[0058] Step 21: Determine the feature information of the target based on satellite imagery;

[0059] Step 22: Based on the feature information, match the target with the three-dimensional models in the target model library, and determine the three-dimensional model that matches the target as the target model.

[0060] Among them, the characteristic information of a target is used to characterize the features or attributes that distinguish one thing from another. The characteristic information of a target can include information such as the target's location, quantity, and type. For example, the characteristic information of a human body can be fingerprints, pupils, limbs, and torso; the characteristic information of a road can be zebra crossings, sidewalks, or motor vehicle lanes; and the characteristic information of a hospital can be the presence of doctors, nurses, or a cross-shaped symbol.

[0061] After obtaining satellite images containing the battlefield environment and targets, the system identifies the targets within the satellite images and recognizes their feature information, thereby distinguishing the targets from other objects and identifying their characteristics or attributes. Next, the target feature information is matched against all 3D models in a target model library. The 3D model that matches the target in the library is used as the target model and stored in a cache for subsequent construction of the 3D simulation scene of the battlefield environment. The target model is used for constructing the 3D simulation scene of the battlefield environment.

[0062] The characteristic information of a target can include its location, quantity, and type. The location of a target mainly includes the size of the area it occupies, the proportion of each smaller target, the overall location of the target, and its geographical information such as latitude and longitude. The quantity of targets is the sum of all targets of various sizes displayed in the satellite image. The type of targets involves classifying them into several major categories, including buildings, roads, airports, equipment, vehicles, and reconnaissance equipment. These categories must be identified and classified using image recognition algorithms.

[0063] In this embodiment, when matching the target with the 3D models in the target model library, the 3D model in the target model library that matches the target is determined by the target's feature information, thereby improving the recognition accuracy of the model that matches the target in the target model library.

[0064] In one embodiment, please refer to Figure 3 Step 21, based on satellite imagery, determine the feature information of the target, including:

[0065] Step 211: Import the satellite image into the battlefield situation map;

[0066] Step 212: Adjust the satellite image to match it with the battlefield situation map;

[0067] Step 213: Based on the adjusted satellite image, determine the feature information of the target.

[0068] Among them, the battlefield situation map is a combat-ready map with battlefield defense markings. The battlefield situation map includes markings of targets, concealed locations, bases, and battle locations.

[0069] Satellite images acquired by satellites are transmitted to data storage devices via communication transmission equipment, analyzed, and then imported into the battlefield situation map. The imported satellite images are then analyzed, and adjustments such as registration and correction are performed according to battlefield image standards to ensure their proportions, size, and other aspects are aligned with the battlefield situation map. Figure 1 To identify targets and their characteristic information, including their location, quantity, and type, by comprehensively utilizing target recognition technologies such as image recognition, machine learning, and human intervention.

[0070] In this embodiment, satellite images of the battlefield environment are imported into the battlefield situation map for adjustment and processing to make the satellite images compatible with the battlefield situation map. Then, the satellite images adapted to the battlefield situation map are used for identification to determine the feature information of the target, thereby improving the identification efficiency and accuracy of the target and its feature information in the satellite images.

[0071] Furthermore, the characteristic information of the target includes the target's location information, quantity information, and type information;

[0072] The location information includes the area of ​​the region where the target is located, the proportion of each small target in the region, and the geographical information of the target.

[0073] The quantity information includes the sum of all targets displayed in the satellite image;

[0074] The category information includes the classification results of the target according to different item types.

[0075] The location of a target mainly includes the size of the area it occupies, the proportion of each smaller target, the overall location of the target, and geographical information such as its latitude and longitude. The number of targets is the sum of all targets of all sizes displayed in the satellite image. The types of targets are classified into several categories, including houses, roads, airports, equipment, vehicles, and reconnaissance equipment. These categories are identified and categorized using image recognition algorithms.

[0076] In one embodiment, determining a target in a satellite image based on the satellite image includes:

[0077] The satellite image is identified using satellite image recognition technology to determine the target within the satellite image.

[0078] By comprehensively utilizing target recognition technologies such as image recognition, machine learning, and human intervention, the target can be identified, including its location, quantity, and type.

[0079] Furthermore, by using satellite image recognition technology, satellite images are identified to determine the characteristic information of targets in the satellite images, and information such as the location, quantity, and type of the targets are identified.

[0080] In one embodiment, please refer to Figure 4 Step 40, after generating strike targets that match the battlefield conditions based on the three-dimensional simulation scene, includes:

[0081] Step 50: Based on the three-dimensional simulation scene, determine the equivalent damage tree of the enemy and friendly targets;

[0082] Step 60: Based on the three-dimensional simulation scene and the equivalent damage tree, determine the equivalent damage criteria for both enemy and friendly targets.

[0083] After constructing the 3D simulation scene, the targets within the scene are identified, and impact simulations are performed to obtain the equivalent damage trees for both friendly and enemy targets. The equivalent damage tree represents the impact simulation results and contains multiple damaged trunks and leaves to demonstrate the impact effect on the targets. Subsequently, the equivalent damage trees in the 3D simulation scene are evaluated to determine the portion of the trees that inflicts a certain level of damage, thus obtaining the equivalent damage criteria for both friendly and enemy targets. The equivalent damage criteria are the portion of the impact simulation results that achieves the desired damage effect.

[0084] In this embodiment, by simulating the impact on targets, the equivalent damage trees and equivalent damage criteria of both friendly and enemy targets are identified. This is beneficial for simulating the impact effect of the battlefield environment on targets, thereby optimizing and correcting the target impact effect for combat personnel. It is conducive to battlefield combat simulation, realizing the simulation exercise of battlefield impact, and providing combat personnel with a visualized combat scene for actual battlefield combat.

[0085] The target reconstruction apparatus based on satellite imagery provided by the present invention is described below. The target reconstruction apparatus based on satellite imagery described below can be referred to in correspondence with the target reconstruction method based on satellite imagery described above.

[0086] Please refer to Figure 5 The target reconstruction device based on satellite imagery proposed in this invention includes:

[0087] The target recognition module 510 is used to determine targets in the satellite image based on the satellite image.

[0088] The model matching module 520 is used to match the target with the three-dimensional models in the target model library, and determine the three-dimensional model that matches the target as the target model;

[0089] Simulation module 530 is used to determine a three-dimensional simulation scene based on the target model;

[0090] The target generation module 540 is used to generate targets that match the battlefield conditions based on the three-dimensional simulation scene.

[0091] Furthermore, the model matching module is also used for:

[0092] Based on satellite imagery, the characteristic information of the target is determined;

[0093] Based on the feature information, the target is matched with three-dimensional models in the target model library, and the three-dimensional model that matches the target is determined as the target model.

[0094] Furthermore, the model matching module is also used for:

[0095] Import the satellite images into the battlefield situation map;

[0096] The satellite imagery is adjusted to match the battlefield situation map.

[0097] Based on the adjusted satellite image, the feature information of the target is determined.

[0098] Furthermore, the characteristic information of the target includes the target's location information, quantity information, and type information;

[0099] The location information includes the area of ​​the region where the target is located, the proportion of each small target in the region, and the geographical information of the target.

[0100] The quantity information includes the sum of all targets displayed in the satellite image;

[0101] The category information includes the classification results of the target according to different item types.

[0102] Furthermore, the target recognition module is also used for:

[0103] The satellite image is identified using satellite image recognition technology to determine the target within the satellite image.

[0104] Furthermore, the target reconstruction device based on satellite imagery also includes a damage simulation module, used for:

[0105] Based on the aforementioned three-dimensional simulation scenario, the equivalent damage trees of both enemy and friendly targets are determined;

[0106] Based on the three-dimensional simulation scene and the equivalent damage tree, the equivalent damage criteria for both enemy and friendly targets are determined.

[0107] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640, wherein the processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions in the memory 630 to execute a target reconstruction method based on satellite imagery. This method includes: determining targets in the satellite imagery; matching the targets with three-dimensional models in a target model library to determine the matching three-dimensional model as the target model; determining a three-dimensional simulation scene based on the target model; and generating strike targets matching the battlefield conditions based on the three-dimensional simulation scene.

[0108] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0109] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the target reconstruction method based on satellite imagery provided by the above methods. The method includes: determining a target in the satellite imagery based on the satellite imagery; matching the target with a three-dimensional model in a target model library to determine a three-dimensional model that matches the target as a target model; determining a three-dimensional simulation scene based on the target model; and generating a strike target that matches the battlefield situation based on the three-dimensional simulation scene.

[0110] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the target reconstruction method based on satellite imagery provided by the above methods. The method includes: determining a target in the satellite imagery based on the satellite imagery; matching the target with a three-dimensional model in a target model library to determine a three-dimensional model that matches the target as a target model; determining a three-dimensional simulation scene based on the target model; and generating a strike target that matches the battlefield conditions based on the three-dimensional simulation scene.

[0111] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0112] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for reconstructing a target based on satellite images, characterized in that, include: Based on satellite imagery, the target in the satellite imagery is determined; The target is matched with three-dimensional models in the target model library, and the three-dimensional model that matches the target is determined as the target model; Based on the target model, a three-dimensional simulation scene is determined; Based on the aforementioned 3D simulation scenario, strike targets matching the battlefield conditions are generated; Based on satellite imagery, the characteristic information of the target is determined, including: Import the satellite images into the battlefield situation map; The satellite imagery is adjusted to match the battlefield situation map. Based on the adjusted satellite image, the feature information of the target is determined; Matching the target with 3D models in a target model library to determine the 3D model that matches the target as the target model includes: Based on satellite imagery, the characteristic information of the target is determined; Based on the feature information, the target is matched with the three-dimensional models in the target model library, and the three-dimensional model that matches the target is determined as the target model; The characteristic information of the target includes the target's location information, quantity information, and type information; The location information includes the area of ​​the region where the target is located, the proportion of each small target in the region, and the geographical information of the target. The quantity information includes the sum of all targets displayed in the satellite image; The category information includes the classification results of the target according to different item types. 2.The satellite image-based target reconstruction method of claim 1, wherein, Based on satellite imagery, the targets in the satellite imagery are determined, including: The satellite image is identified using satellite image recognition technology to determine the target within the satellite image. 3.The satellite image-based target reconstruction method of claim 1, wherein, After generating strike targets that match the battlefield conditions based on the aforementioned 3D simulation scene, the process includes: Based on the aforementioned three-dimensional simulation scenario, the equivalent damage trees of both enemy and friendly targets are determined; Based on the three-dimensional simulation scene and the equivalent damage tree, the equivalent damage criteria for both enemy and friendly targets are determined.

4. A target reconstruction apparatus based on satellite images, characterized in that, include: The target recognition module is used to determine targets in the satellite images based on satellite images; The model matching module is used to match the target with the three-dimensional models in the target model library, and determine the three-dimensional model that matches the target as the target model; The simulation module is used to determine a three-dimensional simulation scene based on the target model; The target generation module is used to generate targets that match the battlefield conditions based on the three-dimensional simulation scene. The model matching module is also used for: Import the satellite images into the battlefield situation map; The satellite imagery is adjusted to match the battlefield situation map. Based on the adjusted satellite image, the feature information of the target is determined; The model matching module is also used for: Based on satellite imagery, the characteristic information of the target is determined; Based on the feature information, the target is matched with the three-dimensional models in the target model library, and the three-dimensional model that matches the target is determined as the target model; The characteristic information of the target includes the target's location information, quantity information, and type information; The location information includes the area of ​​the region where the target is located, the proportion of each small target in the region, and the geographical information of the target. The quantity information includes the sum of all targets displayed in the satellite image; The category information includes the classification results of the target according to different item types.

5. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the target reconstruction method based on satellite imagery as described in any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the target reconstruction method based on satellite imagery as described in any one of claims 1 to 3.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the target reconstruction method based on satellite imagery as described in any one of claims 1 to 3.

Images