Object recognition and object information acquisition system and method using a telescope

Abstract

The object recognition and object information acquisition system and method using a telescope according to the embodiment provides a recognition alarm when a specific object (an opponent's vessel) is recognized while monitoring through a telescope in a naval environment. In addition, in the embodiment, information regarding the object is acquired through artificial intelligence. In the embodiment, the information regarding the object may include the size, year of manufacture, purpose, output, and speed of the vessel. Furthermore, in the embodiment, the distance to the object vessel is predicted by using a calculation formula that combines the size of the captured object based on the information and the actual size of the vessel obtained through AI. Additionally, in the embodiment, an object is recognized in an image captured by a telescope, and information regarding the recognized object is acquired through image search and artificial intelligence.

Description

Technology Field

[0001] The present disclosure relates to a system and method for object recognition and object information acquisition using a telescope. Specifically, it relates to a system and method for recognizing an object through an image captured by a telescope and measuring the distance to the object using a calculation formula based on the size of the recognized object. Background Technology

[0002] Unless otherwise indicated in this specification, the contents described in this section are not prior art for the claims of this application, and are not to be recognized as prior art simply because they are included in this section.

[0003] Conventional telescopes magnify objects through zooming, but as the zoom ratio increases, image resolution decreases, making it difficult to identify detailed information about the objects. Furthermore, distant objects or objects with colors similar to the background are not accurately recognized, and there is a lack of automated recognition systems such as AI.

[0004] Furthermore, conventional methods may suffer from reduced accuracy because they primarily rely on the telescope's magnification and the object's field of view to measure distance. Additionally, since telescopes provide only 2D images, it is difficult to directly measure depth information (3D distance) to an object. This is because sensors (such as lasers or LiDAR) to compensate for this limitation are not integrated. Moreover, measurement errors may occur depending on the object's viewing angle or the telescope's position. Furthermore, observing an object at high zoom levels causes severe shaking (vibration) and image distortion, which lowers the accuracy of distance measurement or object recognition. Additionally, vertical distortion (barrel distortion, pincushion distortion) caused by the telescope's optical system may occur.

[0005] Conventional technology has limitations in calculating and providing distance information in real time after object recognition because it lacks the integration of AI and real-time analysis technologies. In particular, it is difficult to predict the speed and direction of fast-moving objects, such as in maritime or combat situations. Furthermore, object visibility and recognition rates drop significantly in environments with poor lighting conditions, such as at night or during inclement weather (rain, fog, snow). In addition, external environmental factors such as wind, fine dust, and thermal currents adversely affect image capture through telescopes, and during long-distance observations, changes in atmospheric density or turbulence can cause images to shake or become distorted.

[0006] Furthermore, conventional systems simply measure size and distance, and were limited in their ability to analyze object attribute information (type, speed, direction of movement). Due to a lack of AI-based databases or pattern learning, they could not recognize objects that had not been previously learned. Additionally, many conventional technologies were manual, requiring users to observe and estimate distances directly, making automated object recognition and distance calculation difficult. Moreover, high-performance telescopes tended to be large and heavy, resulting in low portability and maneuverability. Prior art literature

[0007] 1. Korean Patent Publication No. 10-2023-0166937 (Dec. 07, 2023) 2. Korean Patent Publication No. 10-2024-0168312 (Nov. 29, 2024) The problem to be solved

[0008] The object recognition and object information acquisition system and method using a telescope according to the embodiment provides a recognition alarm when a specific object (an opponent's vessel) is recognized while monitoring through a telescope in a naval environment.

[0009] In addition, in the practical example, information about the object is obtained through artificial intelligence. In the embodiment, the information about the object may include the size, year of manufacture, purpose, output, and speed of the trap.

[0010] In addition, in the embodiment, the distance to the object trap is predicted by using the size of the object captured based on the relevant information and the size of the actual trap, which is information obtained through AI, in a calculation formula.

[0011] In addition, in the embodiment, an object is recognized in an image captured by a telescope, and information about the recognized object is obtained through image search and artificial intelligence.

[0012] In addition, the embodiment provides an algorithm that calculates the correlation between the zoom ratio and the size of an object when the image is enlarged by zooming. This is intended to perform the correlation calculation between the ratio and the size when zooming is performed, as identification is difficult unless the image is in a high-magnification zoom state.

[0013] In addition, in the embodiment, calculations at high magnification can reduce errors compared to calculations at low magnification. At high magnification, because the telescope provides a narrower field of view, even small movements or positional changes of the observed object appear as larger angles. This helps to make angle measurements more precise and contributes to increasing the precision of the calculation results.

[0014] However, the problem to be solved according to one embodiment is not limited only to that mentioned above. means of solving the problem

[0015] An object recognition and object information acquisition system using a telescope according to an embodiment may include: a telescope that collects monitoring data; and a server that generates an alert and detects detailed information of the object when a specific object including a trap is detected through the analysis of monitoring data collected from the telescope.

[0016] In addition, it can be processed not only on the server but also on the device.

[0017] Additionally, the server includes a memory for storing at least one command for object recognition and object information acquisition using a telescope; and a processor for performing operations according to said command, wherein the processor analyzes monitoring data using an artificial intelligence model to detect detailed information including the size, year of manufacture, purpose, output, and speed of the vessel, and calculates the size of the photographed object and the distance between the telescope and the object through said detected detailed information.

[0018] In addition, the processor can recognize objects through monitoring data acquired from the telescope and obtain information about the recognized objects through image search and artificial intelligence.

[0019] In addition, when the processor magnifies an image acquired from a telescope through zoom, it can calculate the size of the object by considering the zoom magnification.

[0020] In addition, the processor can identify the type, function, and performance of the opponent's trap through the analysis of monitoring data. Effects of the invention

[0021] The object recognition and object information acquisition system and method using a telescope as described above accurately recognizes objects through artificial intelligence (AI) technology and rapidly detects specific objects (e.g., enemy traps).

[0022] In addition, since the embodiment automatically provides a recognition alarm when an object is detected, users can quickly recognize the situation and respond, thereby significantly increasing surveillance efficiency and accuracy in a naval environment.

[0023] In addition, through an example, the actual size of the trap obtained via AI and the size of the object captured by a telescope are applied to the calculation formula to enable accurate distance prediction.

[0024] In addition, the embodiment improves the precision of distance calculation by associating the magnification of an image enlarged via zoom with the size of the object. This significantly improves accuracy compared to triangulation or simple angle-of-view-based distance measurement.

[0025] Furthermore, in the embodiment, various information about an object (size, year of manufacture, purpose, output, speed) can be acquired through artificial intelligence (AI), enabling detailed analysis beyond simple object detection. For example, by identifying the type, function, and performance of an opposing vessel, this information can be utilized for formulating operational plans and strategies.

[0026] In addition, the embodiment enables precise measurement of the distance and size of an object even in a zoomed state through an algorithm that calculates the correlation between the zoom magnification and the object size. This enables accurate object analysis even in long-distance surveillance environments.

[0027] Furthermore, the embodiment enables the overcoming of the limitations of manual monitoring by automatically performing object recognition and analysis through artificial intelligence. Additionally, users can quickly grasp the situation and reduce response time through real-time recognition alarms.

[0028] This significantly improves the operational efficiency and operational capability of the naval surveillance system.

[0029] Furthermore, through the embodiments, object recognition, distance measurement, and information acquisition are all automated, minimizing human error. In addition, it resolves the inefficiency of existing manual distance estimation and provides an advanced automated system.

[0030] In addition, as demonstrated in the example, since the AI ​​recognizes objects based on images captured through a telescope, it can be applied to various fields such as aerial surveillance and ground surveillance as well as marine environments.

[0031] In addition, the combination of zoom and AI analysis technology enables effective operation even in adverse weather or long-distance observation environments.

[0032] The effects obtainable from the exemplary embodiments of the present disclosure are not limited to those mentioned above, and other unmentioned effects can be clearly derived and understood by those skilled in the art to which the exemplary embodiments of the present disclosure belong from the description below. That is, unintended effects resulting from the implementation of the exemplary embodiments of the present disclosure can also be derived by those skilled in the art from the exemplary embodiments of the present disclosure. Brief explanation of the drawing

[0033] FIG. 1 is a drawing showing an object recognition and object information acquisition system using a telescope according to an embodiment. FIG. 2 is a diagram showing the control operation of a telescope according to an embodiment. FIG. 3 is a drawing showing a block diagram of a server according to an embodiment. FIG. 4 is a drawing illustrating a method for object recognition and object information acquisition using a telescope according to an embodiment. Specific details for implementing the invention

[0034] Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Identical or similar components regardless of drawing symbols are assigned the same reference number, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably solely for the ease of drafting the specification and do not inherently possess distinct meanings or roles. Furthermore, in describing embodiments disclosed in this specification, if it is determined that a detailed description of related prior art could obscure the essence of the embodiments disclosed in this specification, such detailed description will be omitted. Additionally, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification; the technical concept disclosed in this specification is not limited by the attached drawings, and it should be understood that they include all modifications, equivalents, and substitutions that fall within the spirit and technical scope of the present invention.

[0035] Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. These terms are used solely for the purpose of distinguishing one component from another.

[0036] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0037] In this application, terms such as “comprising” or “having” are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0038] In this specification, the term "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware.

[0039] Some of the operations or functions described herein as being performed by a terminal, device, or device may instead be performed by a server connected to said terminal, device, or device. Likewise, some of the operations or functions described as being performed by a server may also be performed by a terminal, device, or device connected to said server.

[0040] Hereinafter, the present invention will be described in detail with reference to the attached drawings.

[0041] FIG. 1 is a diagram showing an object recognition and object information acquisition system using a telescope according to an embodiment.

[0042] Referring to FIG. 1, an object recognition and object information acquisition system using a telescope according to an embodiment may be configured to include a server (100) and a telescope (200). The telescope (200) collects monitoring data that monitors specific objects, such as traps. In the embodiment, the telescope (200) performs an automatic focus adjustment function through a high-resolution and high-magnification lens so as to observe objects at a distance. The telescope (200) performs a function of automatically adjusting the focus according to the position of the object. In addition, the telescope (200) according to the embodiment includes a sensor capable of detecting infrared light in addition to visible light so as to observe objects during both day and night.

[0043] Additionally, the telescope (200) performs pan (horizontal rotation), tilt (vertical rotation), and zoom (magnification / reduction) functions through a pan-tilt-zoom (PTZ) function so that it can automatically track an object being monitored when it moves. In the embodiment, the telescope (200) detects when a specific object approaches within a certain distance or movement is detected through a motion sensor and automatically starts monitoring. Additionally, it can trigger monitoring events by detecting specific sounds (e.g., warning sounds, sounds of object collisions, etc.) through an acoustic sensor. Furthermore, the telescope (200) can include temperature changes or environmental changes (humidity, atmospheric pressure, etc.) of a trap or a specific object in the monitoring data. Additionally, the telescope (200) can be integrated with an optical device to capture images and photos. It is used to monitor temperature changes of a specific object through an image data storage system for real-time streaming and record storage.

[0044] Additionally, the telescope (200) performs an artificial intelligence (AI) algorithm that recognizes and tracks objects (such as traps) being monitored through an object detection algorithm. In the embodiment, the telescope (200) learns the appearance and movement patterns of specific objects and automatically detects objects based on this. Furthermore, through an anomaly detection algorithm, it analyzes specific conditions (movement, sound, temperature change, etc.) when they occur to detect abnormal situations. Additionally, the telescope (200) collects images, sensor data, and movement information of objects in real time. Afterward, the data can be transmitted to a local device (e.g., DVR) or a cloud server for storage. Additionally, data is recorded when certain conditions (events) occur. For example, if an object approaching a trap is detected, data is recorded from that moment on.

[0045] In the embodiment, a monitoring device including a telescope (200) can be remotely controlled from a smartphone, PC, tablet, etc.

[0046] FIG. 2 is a diagram illustrating the control operation of a telescope according to an embodiment. Referring to FIG. 2, in the embodiment, the shooting height and shooting angle of the telescope (200) can be adjusted by remote control of an administrator terminal or a user terminal. Additionally, the telescope (200) can automatically adjust the shooting height and shooting angle depending on whether an object is detected. Furthermore, in the embodiment, a warning notification is sent to the user when a specific condition (e.g., approach of an object, occurrence of noise, etc.) occurs. In the embodiment, when a specific event occurs, an email, message, or push notification can be sent to the user via the administrator terminal.

[0047] In the embodiment, the telescope (200) defines the area to be observed and the object to be observed (e.g., a trap). Subsequently, the autofocus and pan-tilt-zoom (PTZ) functions are initialized. Additionally, equipment such as a camera, sensor, and telescope observes the target area, and when motion, sound, or temperature change is detected, the monitoring state is activated. Furthermore, when an object is detected, the object is recognized and tracked through an AI algorithm, and the camera's field of view automatically follows the object using the pan-tilt-zoom (PTZ) function. Additionally, the telescope (200) collects data such as the object's image, location, temperature, and sound in real time and stores it on a local or cloud server. The data is stored for real-time streaming as needed or for later playback. Subsequently, when situations such as the object's approach, motion detection, or temperature anomalies occur, a notification (push notification, SMS, email, etc.) is sent to the user, and the user can check the site in real time through a remote control app or software.

[0048] The server (100) generates a notification when a specific object containing a trap is detected through the analysis of monitoring data collected from the telescope, and detects detailed information of the object.

[0049] In an embodiment, the server (100) provides a technology for detecting specific objects, including traps, in real time by analyzing data collected through a telescope (200). Additionally, it analyzes detailed information about the detected objects and provides it to the user. If the detected objects satisfy specific conditions, the server (100) generates a warning notification to inform the user. Furthermore, it optimizes system performance through the efficient storage and analysis of monitoring data.

[0050] In the embodiment, the server (100) receives and stores data collected from the telescope and performs object detection and analysis. Subsequently, it detects specific objects using an AI-based object recognition algorithm and an anomaly detection algorithm. It also generates detailed information by analyzing the attributes of the object (size, location, speed, temperature, etc.). Additionally, when a specific object is detected by the server (100), it notifies the user in the form of a warning. In the embodiment, real-time object information is visually provided to the user through a user interface (UI). Additionally, the user can remotely control the telescope or check the data analysis results. In the embodiment, the telescope (200) captures images in real time and transmits infrared and optical data to the server (100). The data includes high-resolution images, thermal image data, distance information, etc. The server (100) inputs the received data into an AI-based object recognition model for analysis. The object recognition model detects specific objects through the following process. Additionally, it filters the image data, removes noise, detects the shape of the object, and generates a bounding box. Additionally, it classifies objects within the bounding box into traps, vehicles, animals, etc. In the embodiment, information such as the size, location, movement speed, and temperature of the detected object is analyzed. To this end, distance measurement data from the telescope (200) is utilized. Subsequently, if the object is a trap, the type is identified by comparing the structural features of the trap (e.g., thermal image data of the trap cover). Additionally, the server (100) generates a warning notification when specific conditions are met (e.g., the trap is located within a certain distance, movement is detected, etc.). The notification includes detailed information about the object (e.g., object type, location coordinates, attributes, etc.). The notification is transmitted to the user in real time. The server (100) stores the data of the detected object on a local or cloud server. The stored data can be analyzed and provided in the form of a daily report or an event report.

[0051] Figure 3 is a diagram showing a block diagram of a server according to an embodiment.

[0052] In the embodiment, a server is a computing system that provides services to other computers or devices in a computer network or stores and manages data. The server (200) accepts requests from other computers or devices called clients and provides responses or data to those requests. The configuration of the server (200) shown in FIG. 2 is merely a simplified example.

[0053] The communication module (110) can be configured regardless of the mode of communication, such as wired or wireless, and can be configured with various communication networks, such as a Personal Area Network (PAN) or a Wide Area Network (WAN). Additionally, the communication module (110) can operate based on the known World Wide Web (WWW) and may utilize wireless transmission technologies used for short-range communication, such as Infrared Data Association (IrDA) or Bluetooth. For example, the communication module (110) may be responsible for transmitting and receiving data necessary to perform a technique according to one embodiment of the present disclosure.

[0054] Memory (120) may refer to any type of storage medium. For example, memory (120) may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk. Such memory (120) may also constitute the database shown in FIG. 1.

[0055] The memory (120) can store at least one instruction that can be executed by the processor (130). Additionally, the memory (120) can store any form of information generated or determined by the processor (130) and any form of information received by the server (200). Additionally, the memory (120) stores various types of modules, instruction sets, or models.

[0056] The processor (130) can perform technical features according to embodiments of the present disclosure to be described below by executing at least one instruction stored in memory (120). In one embodiment, the processor (130) may be composed of at least one core and may include a processor for data analysis and / or processing, such as a central processing unit (CPU) of a computer device, a general purpose graphics processing unit (GPGPU), or a tensor processing unit (TPU).

[0057] This processor (130) can train a neural network or model designed in a machine learning or deep learning manner. To this end, the processor (130) can perform calculations for training the neural network, such as processing input data for training, extracting features from input data, calculating errors, and updating the weights of the neural network using backpropagation. Additionally, the processor (130) can perform inference for a specific purpose using a model implemented in an artificial neural network manner.

[0058] Additionally, the processor (130) analyzes monitoring data using an artificial intelligence model to detect detailed information including the size, age, purpose, output, and speed of the vessel, and calculates the size of the captured object and the distance between the object and the telescope through the detected detailed information. In the embodiment, the processor (130) provides an AI-based analysis system capable of automatically detecting detailed information regarding the age, purpose, output, and speed. It provides an algorithm that automatically calculates the size of the captured object and its actual size, thereby minimizing measurement errors and improving accuracy. Furthermore, it enables more precise measurement of the actual size through 3D analysis and distance measurement of the object.

[0059] In the embodiment, the telescope (200) magnifies a distant trap through a high-magnification optical device to provide a clear image. Additionally, it can detect the characteristics of an object even in nighttime or low-light environments through an infrared (IR) camera. Furthermore, the telescope (200) detects the distance to the target object through image data and artificial intelligence analysis of the image data, providing data necessary for calculating the actual size of the captured object. In the embodiment, the processor (130) is equipped with an AI model that performs object recognition, object size measurement, age determination, usage analysis, output, and speed calculation. Additionally, it analyzes data received from the telescope (200) to detect the boundary area (bounding box) of the object and extracts the characteristics of the object. Furthermore, to calculate the size of the captured object, it estimates the actual size using 3D position data (distance measurement value) and the pixel size of the captured image. To this end, the telescope (200) obtains basic information necessary for distance prediction. Basic information may include the actual size of the object (e.g., width, height, diameter, etc.), the magnification of the telescope (e.g., 200x), the resolution of the sensor (pixel size, sensor size, etc.), and the size of the object on the screen (measured in pixels or angles). Subsequently, the telescope (200) detects the bounding box of the object and measures the width or height in pixels. Then, the telescope (200) converts the size on the screen into angles using the magnification and sensor characteristics. Through this, the telescope (200) predicts the distance to the object using the collected information.

[0060] In the embodiment, the database (120) holds a pre-trained dataset for various types of vessels (e.g., type, size, year of manufacture, purpose, etc.). Additionally, prior information related to the year of manufacture, output, and speed of the vessels is stored and used for comparative analysis with the features of the detected objects. In the embodiment, a warning notification is sent so that the user can check detailed information regarding the size, year of manufacture, purpose, output, and speed of the vessels. In the embodiment, the warning notification includes detailed information about the objects and the results of comparing the object size with the actual size.

[0061] Additionally, the telescope (200) collects monitoring data in real time. The collected data consists of high-resolution images, 3D distance data, infrared data (IR), thermal image data, etc. In the embodiment, the collected data is transmitted to the processor (130). In the embodiment, the AI ​​model analyzes the received image data to detect an object (a trap). It recognizes the outline (bounding box) of the object and extracts information regarding the shape, structure, size, speed, and age of the trap. The speed of the object is calculated through the change in the object's position in consecutive frames. In addition, the processor (130) detects detailed information about the object through the following process. In the embodiment, size measurement: the actual size (R) is calculated using the pixel size (P) and distance (D) data of the object's bounding box.

[0062] Mathematical formula 1

[0063] R=P*D / FR

[0064] In Equation 1, R is the actual size (unit: m), P is the pixel size of the captured object (unit: px), D is the distance between the telescope and the object (unit: m), and F is the focal length of the telescope (unit: m)

[0065] Subsequently, the processor (130) estimates the age of the trap by comparing the external features of the object (surface wear, external color, etc.) with a pre-trained database. Additionally, it determines the purpose of the trap through its shape and structure (e.g., pit type, cover type, etc.). The movement speed of the object is calculated using the coordinate difference and time of consecutive frames, and a warning notification is generated if a specific speed is exceeded. Subsequently, the actual size (R) of the object is calculated using the object's distance information measured by a 3D distance measuring device and the object's bounding box size (P) detected by the AI ​​model. In the embodiment, the length, height, and width of the trap are accurately measured and compared to the actual size. Additionally, the server sends information regarding the size, age, purpose, output, and speed of the detected object to the user as a notification. The notification includes information such as the size of the detected trap (in meters), the age and purpose of the trap, output and speed, and the location coordinates (GPS information) of the trap. This information can be automatically generated as a PDF report and stored in a management system.

[0066] Additionally, the processor (130) recognizes an object through monitoring data obtained from a telescope and obtains information about the recognized object through image search and artificial intelligence.

[0067] In the embodiment, monitoring data acquired from a telescope is analyzed through an AI-based object recognition system to enable real-time recognition of specific objects. Information about the recognized objects (name, model name, purpose, year of manufacture, etc.) is automatically acquired through an image search system. Furthermore, detailed information about the objects is provided to the user through the integration of an AI analysis algorithm with a database (DB). Additionally, a real-time data analysis and notification system is implemented to send notifications to the user when specific conditions are met.

[0068] In the embodiment, the processor (130) performs AI-based object recognition. In the embodiment, collected data is analyzed to recognize the boundaries and features of the object. Subsequently, based on the external appearance (features, color, shape, outline, etc.) of the recognized object, a query is sent to an image search engine to search for information about the object. Additionally, the form and features of the object are recognized, and information such as the object's type, purpose, model name, and year of manufacture is determined by comparing it with a training database (DB). Subsequently, the image search results and the AI ​​analysis results are integrated to finally provide detailed information about the object (size, purpose, model name, year of manufacture, attributes, etc.) to the user. Furthermore, image and feature data of various objects are pre-learned and stored. Additionally, information such as the object's name, purpose, model name, size, year of manufacture, and characteristics is stored and used by the AI ​​model to identify the object. In the embodiment, the user interface (UI) visually provides the user with detailed information, images, descriptions, year of manufacture, and purpose of the object. Additionally, an interface is provided that allows the user to remotely operate the telescope (200), enabling tracking or zooming in on a specific object. In the embodiment, a telescope (200) monitors a specific area and transmits high-resolution images, infrared data, and 3D distance measurement data in real time to a processor (130). Subsequently, the processor (130) uses an AI object recognition model to recognize the outline of an object in the monitoring data and generates a bounding box. The external appearance of the object (size, shape, color, etc.) is analyzed and converted into a feature vector. The AI ​​model compares this feature vector with a learned database (DB) to determine the type, category, and use of the object.

[0069] In the embodiment, the image search module of the processor (130) converts a feature vector into a search query and transmits the query to an external or local image database. The image search engine returns images with similar appearances and metadata (model name, purpose, year of manufacture, etc.) of the corresponding images. Additionally, the processor (130) integrates the AI ​​object recognition results and the image search results to generate final object information. It obtains information such as the model name, purpose, year of manufacture, and manufacturer of the detected object and provides it visually to the user. For example, it outputs a description such as, "This object is a Model X-200 vessel produced in 2022, equipment used for maritime defense."

[0070] In addition, it visually provides the user with object information (name, model name, purpose, year of manufacture, related images, etc.) through the user interface (UI). Furthermore, it sends warning notifications to the user when specific conditions are met (e.g., a hazardous object is detected, a new type of trap is detected, etc.).

[0071] Additionally, when the processor (130) magnifies an image acquired from a telescope through zoom, it calculates the size of the object by considering the zoom magnification. In an embodiment, the processor (130) can calculate the distance of the object based on the principles of a telescope and an optical device. At this time, the processor (130) calculates the distance (D) between the telescope and the object using the size of the object in the image (in pixels), the angle (θ) occupied by the object (in radians or degrees), and the previously known size of the object.

[0072] The distance between the telescope and the object can be calculated using mathematical formula 2.

[0073] Mathematical formula 2

[0074]

[0075] In the embodiment, the processor (130) detects an object, generates a bounding box, and measures the width and height of the bounding box in pixels. Then, using the focal length f of the telescope, the size on the screen is converted into an angle. In the embodiment, if the actual size W of the object is known, the distance D can be calculated through Equation 3.

[0076] Mathematical formula 3

[0077]

[0078] Existing object size calculation systems rely on fixed-magnification telescopes or cameras, and have limitations in accurately measuring size when zoom functions are applied. In particular, since the field of view (FOV) changes depending on the zoom magnification, size distortion occurs when analyzing images enlarged using zoom.

[0079] To solve this problem, the processor (130) applies a mathematical correction algorithm including zoom magnification information to calculate the actual size of the accurate object.

[0080] In the embodiment, the processor (130) provides a system that calculates the accurate size of an object by reflecting the change in the angle of view according to the zoom magnification. Through a correction algorithm based on the zoom magnification, the ratio between the pixel size of the enlarged object and its actual size can be accurately calculated. In addition, by utilizing a 3D distance measuring device, the actual size can be precisely calculated by combining the zoom magnification and the distance of the object.

[0081] In the embodiment, the processor (130) executes an algorithm to calculate the actual size of an object by correcting the change in pixel size according to the zoom magnification through a zoom correction algorithm. Additionally, the size of the object is accurately calculated by combining the distance information between the telescope and the object and the zoom magnification through a distance correction algorithm. Furthermore, the pixel size of the enlarged object is calculated through an object size calculation module, and the actual size (R) is calculated by considering the zoom magnification and distance information.

[0082] Additionally, in the embodiment, data on the change in the angle of view according to the zoom magnification is stored, and new angle of view information is provided to the processor (130) when the zoom magnification is changed. This includes the angle of view of the telescope, focal length, and data on the conversion ratio between distance and pixels according to the zoom magnification. In the embodiment, the user interface visually provides the user with information on the zoom magnification, distance, size, and location of an object. The user can directly adjust the zoom magnification, and the actual size information of the object is updated in real time according to the adjusted zoom magnification.

[0083] Additionally, the telescope (200) monitors an object in a specific area, and the zoom magnification is changed from 1x to Nx. In the embodiment, when the zoom magnification is changed, the processor (130) receives information on the zoom magnification (Z), field of view (FOV), and distance (D) from the telescope (200).

[0084] When the zoom magnification (Z) changes, the field of view (FOV) changes according to Equation 2.

[0085] Mathematical formula 4

[0086] FOVnew=FOVbase / Z

[0087] In Equation 4, FOVbase is the base angle of view (angle of view at zoom 1x), FOVnew is the new angle of view when the zoom magnification is changed to Z, and Z is the result of measuring the pixel size (P) of the zoomed object. The pixel size (P) of the object is measured in the image of the magnified object. For example, after recognizing the outline of the object with a bounding box, the horizontal pixel size (Px) and the vertical pixel size (Py) are measured. In the embodiment, the processor (130) calculates the actual size (R) of the object using the zoom magnification (Z), angle of view (FOV), distance (D), and pixel size (P). The actual size (R) of the object is calculated by Equation 3.

[0088] Mathematical formula 5

[0089]

[0090] In Equation 5, R is the actual size of the object (m), P is the pixel size of the object measured in the image (px), and D is the distance between the telescope and the object (m). FOVnew is the new angle of view based on the zoom magnification (degrees, rad), and Sensor Size is the size of the camera's image sensor (mm).

[0091] N is the number of pixels (px) based on camera resolution.

[0092] In the embodiment, information such as the calculated object size, distance, and zoom scale is displayed on the user interface (UI). Additionally, a warning notification is sent to the user when specific conditions are met (e.g., a dangerous object is detected, an object larger than a certain size is recognized, etc.).

[0093] In the embodiment, accurate size calculation based on the zoom ratio is possible, allowing the actual size of an object to be accurately calculated even when the zoom is changed. Real-time calculation: Since calculations are performed immediately when the zoom ratio changes, real-time size information can be provided to the user. Additionally, improved monitoring accuracy: Since the accurate size can be estimated even when the object is magnified through zoom, it can be usefully utilized in security systems, military surveillance, and industrial monitoring. In the embodiment, the processor (130) identifies the type, function, and performance of the opposing vessel through the analysis of monitoring data. The type of the vessel is automatically determined through an AI object recognition model. Furthermore, to analyze the function of the vessel (offensive type, defensive type, multi-purpose, etc.), structural features and operation patterns are identified. Additionally, to predict the performance of the vessel (speed, output, detection range, etc.), performance is analyzed based on external information and operation data (speed, rotation angle, etc.). Data analysis and warning notifications are provided in real time to automatically evaluate the risk level of the opposing vessel. Furthermore, the processor (130) recognizes the type, function, and characteristics by analyzing the external appearance of the vessel through an object recognition AI module. Furthermore, the function analysis module analyzes structural features and operational patterns to classify functions into offensive, defensive, and multi-purpose types. Additionally, the performance prediction module analyzes speed, output, detection range, and response capabilities to predict the vessel's performance. Moreover, the risk assessment module calculates the risk level of opposing vessels based on the analyzed function and performance data. The database (DB) linkage module acquires detailed object information by comparing it with learned vessel images, structural data, and performance data. Additionally, the vessel's external appearance information (outline, size, color, structure, equipment status, etc.) and type (offensive, defensive, etc.) are stored as pre-trained data. Furthermore, information regarding each vessel's speed, output, detection range, and mounted equipment is stored.Structural feature data necessary to determine the function (offensive, defensive, support, etc.) of a specific vessel is stored. In the embodiment, the type, function, performance, and risk level of the vessel are visually provided to the user. The attributes, detection range, response capability, and other related information of the vessel are delivered to the user in the form of notifications. Additionally, a telescope (200) monitors the vessel in a specific area and transmits high-resolution images, infrared data, and 3D distance data to the processor (130). In the embodiment, an object recognition module analyzes the outline and features (size, shape, color, onboard equipment, etc.) of the vessel to determine the type of vessel.

[0094] The AI ​​object recognition model generates the outline of the vessel as a bounding box, converts it into a feature vector, and compares it with a DB to determine the type of vessel (e.g., small vessel, high-speed boat, destroyer, etc.). Subsequently, the processor (130) analyzes the structural characteristics of the vessel (types of mounted weapons, sensors, equipment, etc.) and classifies its function into offensive, defensive, multi-purpose, etc. In the embodiment, if a specific weapon (e.g., radar equipment, missile launcher, etc.) is detected, it is determined to be an offensive vessel. It analyzes the vessel's movement pattern (movement path, rotation angle, etc.) to determine whether it is a defensive or offensive vessel. Subsequently, the processor (130) measures the change in the vessel's position in consecutive frames to calculate the speed. Additionally, it estimates the output (horsepower, kW, etc.) through the vessel's size, engine characteristics, and sound data. Furthermore, it analyzes the characteristics of the sensors and radar equipment mounted on the vessel to estimate the detection range. Additionally, the processor (130) evaluates the risk level based on analyzed data (type, function, performance of the vessel). Additionally, the risk level is evaluated in four stages: normal, caution, warning, and emergency, and a notification is sent to the user. Additionally, the type, function, performance, and risk level of the vessel are provided to the user in real time through a user interface (UI). When specific conditions are met (e.g., the risk level is in an emergency state, detection of a vessel moving at high speed, etc.), a warning notification is sent to the user.

[0095] Below, we will look at FIG. 4. The object recognition and object information acquisition method using a telescope illustrated in FIG. 4 can be performed by a server (100) including a processor (130).

[0096] Meanwhile, FIG. 4 is merely illustrative, and the concept of the present invention is not to be interpreted as being limited to that shown in FIG. 4. For example, each step may be configured in a different order than that shown in FIG. 4, at least one of the steps shown in FIG. 4 may not be performed, or one or more steps not shown in FIG. 4 may be additionally performed.

[0097] Below, the method for object recognition and object information acquisition using a telescope will be described in order. Since the operation (function) of the method for object recognition and object information acquisition using a telescope according to the embodiment is essentially the same as the function of the system, descriptions that overlap with FIGS. 1 to 3 will be omitted.

[0098] FIG. 4 is a diagram illustrating an object recognition and object information acquisition method using a telescope according to an embodiment.

[0099] Referring to FIG. 4, in step S110, monitoring data is analyzed by an artificial intelligence model to detect detailed information including the size, year of manufacture, purpose, output, and speed of the vessel; in step S120, an object is recognized through monitoring data acquired from a telescope; and in step S130, information about the recognized object is obtained through image search and artificial intelligence. In the embodiment, information about the object may include the distance from the telescope to the object. The object recognition and object information acquisition system and method using a telescope as described above accurately recognizes an object through artificial intelligence (AI) technology and rapidly detects a specific object (e.g., an opposing vessel).

[0100] In addition, since the embodiment automatically provides a recognition alarm when an object is detected, users can quickly recognize the situation and respond, thereby significantly increasing surveillance efficiency and accuracy in a naval environment.

[0101] In addition, through an example, the size of an object captured by a telescope, obtained via AI, is applied to a calculation formula to enable accurate distance prediction.

[0102] In addition, the embodiment improves the precision of distance calculation by associating the magnification of an image enlarged via zoom with the size of the object. This significantly improves accuracy compared to triangulation or simple angle-of-view-based distance measurement.

[0103] Furthermore, in the embodiment, various information about an object (size, year of manufacture, purpose, output, speed) can be acquired through artificial intelligence (AI), enabling detailed analysis beyond simple object detection. For example, by identifying the type, function, and performance of an opposing vessel, this information can be utilized for formulating operational plans and strategies.

[0104] Conventional telescopes struggled with accurate identification due to shaking and reduced resolution at high zoom levels. However, an algorithm that correlates zoom magnification with object size enables precise measurement of object distance and size even while zoomed in. This facilitates accurate object analysis even in long-distance surveillance environments.

[0105] Furthermore, the embodiment enables the overcoming of the limitations of manual monitoring by automatically performing object recognition and analysis through artificial intelligence. Additionally, users can quickly grasp the situation and reduce response time through real-time recognition alarms.

[0106] This significantly improves the operational efficiency and operational capability of the naval surveillance system.

[0107] Furthermore, through the embodiments, object recognition, distance measurement, and information acquisition are all automated, minimizing human error. In addition, it resolves the inefficiency of existing manual distance estimation and provides an advanced automated system.

[0108] In addition, as demonstrated in the example, since the AI ​​recognizes objects based on images captured through a telescope, it can be applied to various fields such as aerial surveillance and ground surveillance as well as marine environments.

[0109] In addition, the combination of zoom and AI analysis technology enables effective operation even in adverse weather or long-distance observation environments.

[0110] Meanwhile, the methods according to the various embodiments of the present invention described above can be implemented in the form of an application or software program that can be installed on an existing electronic device.

[0111] In addition, the whole or part of the method may be composed of multiple software function modules and implemented on an operating system (OS). Alternatively, each step may be composed of a single software function module, or each step may be combined to form a single software function module and implemented on an operating system. Therefore, even if all of the embodiments of the present disclosure are not implemented as a single software function module, if multiple software function modules implement each step of the present disclosure and multiple software function modules are implemented on a single operating system, it can be understood that the method of the present disclosure has been implemented.

[0112] In addition, the methods according to the various embodiments of the present invention described above can be implemented solely through software upgrades or hardware upgrades of existing electronic devices. Furthermore, the various embodiments of the present invention described above can also be performed through an embedded server equipped in an electronic device or an external server of the electronic device.

[0113] Meanwhile, according to one embodiment of the present invention, the various embodiments described above may be implemented as software comprising instructions stored on a computer-readable recording medium using software, hardware, or a combination thereof. In some cases, the embodiments described herein may be implemented as the processor itself. According to the software implementation, embodiments such as the procedures and functions described herein may be implemented as separate software modules. Each of the software modules may perform one or more functions and operations described herein.

[0114] Meanwhile, a computer or a similar device may include a device according to the disclosed embodiments, which is capable of calling instructions stored from a storage medium and operating according to the called instructions. When said instructions are executed by a processor, the processor may perform a function corresponding to said instructions directly or by using other components under the control of said processor. The instructions may include code generated or executed by a compiler or an interpreter.

[0115] A computer-readable recording medium may be provided in the form of a non-transitory computer-readable recording medium. Here, "non-transitory" simply means that the storage medium does not contain a signal and is tangible, without distinguishing whether data is stored semi-permanently or temporarily on the storage medium. In this context, a non-transitory computer-readable medium refers to a medium that stores data semi-permanently and is readable by a device, rather than a medium that stores data for a short moment, such as registers, caches, or memory. Specific examples of non-transitory computer-readable media may include CDs, DVDs, hard disks, Blu-ray discs, USBs, memory cards, and ROMs.

[0116] As described above, exemplary embodiments have been disclosed in the drawings and specification. Although specific terms have been used to describe the embodiments in this specification, they are used only for the purpose of explaining the technical concept of this disclosure and are not intended to limit the meaning or the scope of this disclosure as defined in the claims. Therefore, those skilled in the art will understand that various modifications and equivalent alternative embodiments are possible therefrom. Accordingly, the true technical scope of protection of this disclosure should be determined by the technical concept of the appended claims.

Claims

Claim 1 An object recognition and object information acquisition system using a telescope, comprising: a telescope for collecting monitoring data; and a server for generating an alert and detecting detailed information of said object when a specific object including a trap is detected through the analysis of monitoring data collected from said telescope. Claim 2 In claim 1, the server comprises a memory for storing at least one command for object recognition and object information acquisition using a telescope; and a processor for performing operations according to said command, wherein the processor analyzes monitoring data using an artificial intelligence model to detect detailed information including the size, year of manufacture, purpose, output, and speed of a vessel, and calculates the size of a photographed object and the distance between the object and the telescope through said detected detailed information, thereby forming an object recognition and object information acquisition system using a telescope. Claim 3 In paragraph 2, the above processor recognizes an object through monitoring data acquired from a telescope and acquires information about the recognized object through image search and artificial intelligence, an object recognition and object information acquisition system using a telescope. Claim 4 In paragraph 3, the above processor calculates the size of an object by considering the zoom magnification when an image acquired from a telescope is enlarged through zoom, an object recognition and object information acquisition system using a telescope. Claim 5 In paragraph 3, the processor is an object recognition and object information acquisition system using a telescope that identifies the type, function, and performance of the opposing vessel through the analysis of monitoring data. Claim 6 A method for object recognition and object information acquisition using a telescope, comprising: a step of collecting monitoring data from a telescope; and a step of generating an alert and detecting detailed information of said object when a specific object including a trap is detected through analysis of the monitoring data collected from said telescope at a server. Claim 7 In claim 6, the step of detecting detailed information of the object comprises: a step of detecting detailed information including the size, year of manufacture, purpose, output, and speed of the vessel by analyzing monitoring data with an artificial intelligence model; and a step of calculating the size of the object captured through the detected detailed information and the distance between the object and the telescope; a method for object recognition and object information acquisition using a telescope. Claim 8 In claim 7, the step of detecting detailed information of the object is a method for object recognition and object information acquisition using a telescope, wherein the object is recognized through monitoring data acquired from a telescope, and information about the recognized object is acquired through image search and artificial intelligence. Claim 9 In claim 8, the step of detecting detailed information of the object involves calculating the size of the object by considering the zoom magnification when an image acquired from a telescope is enlarged through zoom, in a method for object recognition and object information acquisition using a telescope. Claim 10 In claim 8, the step of detecting detailed information of the object is a method for object recognition and object information acquisition using a telescope, which identifies the type, function, and performance of the opposing vessel through monitoring data analysis.

Images