KR20210105180A - Apparatus and method for target detecting - Google Patents

Abstract

The present invention relates to a device and method for detecting a target capable of more reliable target identification and acquisition by superimposing or linking images acquired from a plurality of optics to reconstruct a battlefield and place a target. According to one embodiment of the present specification, the method for detecting a target includes the steps of: collecting images acquired from a plurality of guided missiles; reconstructing an image by superimposing and linking the plurality of collected images; identifying a plurality of targets in the reconstructed image and assigning IDs to be assigned to the plurality of guided missiles to classify the targets; and transmitting target information including identification information of the target and the ID to the plurality of guided missiles.

Description

Target detection device and method {APPARATUS AND METHOD FOR TARGET DETECTING}

The present invention relates to a target detection apparatus and method, and to a target detection apparatus and method capable of more reliable target identification and acquisition by superimposing or connecting images obtained from a plurality of optics to reconstruct a battlefield and arranging a target will be.

Conventional general guided missiles perform a single mission of tracking a single target after acquiring one target through an optical device, are given a mission, are loaded with information, and are fired according to a preset procedure. Thereafter, the launched guided missile detects or acquires a target according to an operation concept for target detection, a guidance method, and the like.

However, when a situation arises in which multiple targets must be acquired, target information such as the location, distance, and speed of the targets, the location, posture, speed, viewing angle error of the guided missile, and delay time for re-executing the procedure As a result, a problem arises in obtaining all targets with high reliability.

According to an embodiment of the present invention, it is an object to provide a target detection apparatus and method capable of more reliable target identification and acquisition by superimposing or connecting images obtained from a plurality of optics to reconstruct the battlefield and place the target do it with

Another object of the present invention is to provide a target detection apparatus and method capable of acquiring a plurality of targets existing in a wider area by acquiring an image through a plurality of optics according to an embodiment of the present invention.

However, the object of the present invention is not limited to the above, and other objects not mentioned will be clearly understood by those skilled in the art from the following description.

A target detection apparatus according to an embodiment of the present specification includes a target database in which information about a target is stored; a sensor unit that acquires an image including the posture information and the target of the guided missile; an image preprocessor for performing a preprocessing process for extracting target information from the image acquired through the sensor unit and generating target information; an image processing unit for generating image information by reconstructing the image obtained from the sensor unit based on the posture information obtained through the sensor unit and target information extracted through the image preprocessing unit; and a target acquisition unit that searches for a target from the reconstructed image through the image processing unit and acquires the target by comparing it with target information in the target database.

Preferably, the image processing unit estimates the distance to the target using the incident angle, the traveling direction, and the target information of the guided missile, sets the traveling direction of the guided missile as a central point, and converts the distance to the target into vector data, It is characterized in that the image information is generated.

Preferably, the image preprocessor separates the target and the background from the image acquired through the sensor unit, extracts a feature point, generates a two-dimensional target model, searches for a target based on the feature point and the target model, and It is characterized in that the target is determined by comparing the target information stored in the target database, and the target information is generated through the determined target direction and speed information.

In addition, the device may further include a communication unit for receiving target information and image information from the outside.

Preferably, the image processing unit receives a plurality of image information, target information and coordinate vectors respectively generated from a plurality of adjacent guided missiles through the communication unit, and superimposes the received plurality of image information with the generated image information; Connecting to reconstruct a virtual two-dimensional battlefield image, identifying a plurality of targets in the virtual two-dimensional battlefield image with reference to the target information, assigning IDs to be respectively disposed on the plurality of guided missiles, and identification information of the target and target information including the ID is transmitted to the plurality of guided missiles through the communication unit.

In addition, in an embodiment of the present specification, the target detection method includes: a first step of acquiring an image through an image sensor, detecting a target with reference to a target database, and generating target information; a second step of generating image information by reconstructing the acquired image with reference to the guided missile attitude information and position information measured from the inertial measuring device; a third step of receiving a plurality of image information, target information, and coordinate vectors respectively generated from a plurality of adjacent missiles; a fourth step of reconstructing a virtual two-dimensional full-length image by overlapping and linking the plurality of image information received in the third step with the image information generated in the second step; A fifth step of identifying a plurality of targets in the virtual two-dimensional battlefield image with reference to the target information, and assigning IDs to be respectively disposed on the plurality of guided missiles to classify the targets: and the identification information of the targets and the IDs and a sixth step of transmitting the included target information to the plurality of guided missiles.

Preferably, the target information is vector data indicating the direction and speed of the target, and the image information is converted into vector data by estimating the distance to the target using the incident angle, traveling direction, and target information of the guided missile, and setting the center point It is characterized in that it is a two-dimensional virtual battlefield data.

Preferably, the first step comprises: acquiring an image through an image sensor; generating a two-dimensional target model after extracting feature points by separating the target and the background from the acquired image; determining a target by searching for a target through the feature point and the target model and comparing it with target information stored in a target database; and generating target vector data based on the determined target direction and velocity information.

According to an embodiment of the present invention, by superimposing or connecting images obtained from a plurality of optics to reconstruct the battlefield and place the target, there is an effect that more reliable target identification and acquisition is possible.

In addition, according to an embodiment of the present invention, there is an effect of acquiring a plurality of targets existing in a wider area by acquiring an image through a plurality of optics.

1 is a flowchart sequentially illustrating a plurality of target detection methods according to an embodiment of the present invention.
2 is a configuration diagram for explaining a process of acquiring a target in the target detection apparatus according to an embodiment of the present invention.
3 is a flowchart sequentially illustrating a process of generating target vector data according to an embodiment of the present invention.
4 is a flowchart sequentially illustrating a virtual battlefield data generation process according to an embodiment of the present invention.
5 is a flowchart sequentially illustrating a process of simultaneously acquiring a plurality of targets according to an embodiment of the present invention.
6 and 7 are reference diagrams for explaining an image block allocation process and results for target acquisition in an actual battlefield environment according to an embodiment of the present invention.
8 is a block diagram schematically illustrating the configuration of a target detection apparatus according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. First of all, it should be noted that in adding reference numerals to the components of each drawing, the same components are given the same reference numerals as much as possible even though they are indicated on different drawings. In addition, in describing the present invention, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description thereof will be omitted. In addition, preferred embodiments of the present invention will be described below, but the technical spirit of the present invention is not limited thereto and may be variously implemented by those skilled in the art without being limited thereto.

1 is a flowchart sequentially illustrating a plurality of target detection methods according to an embodiment of the present invention.

This embodiment assumes a situation in which a plurality of guided missiles are operated in order to acquire and strike a plurality of targets, and in this case, it is assumed that one Master bullet and the remaining plurality of slave bullets exist among the plurality of guided missiles.

First, each of the optics mounted on a plurality of guided missiles acquires an image with an image sensor to detect a target. Thereafter, the target vector data indicating the direction and speed of the target data and the coordinate vector data and image of the guided missile are transmitted to one master bullet.

The master bullet collects images by receiving images and data obtained from a plurality of optics (S101).

The overlapping parts of the collected images are overlapped, and the non-overlapping parts are connected to reconstruct an image of the battlefield (S103).

Thereafter, a plurality of targets present in the reconstructed image with reference to the target information of the target database are identified in the image and the target is distinguished by assigning a unique number (S105).

Thereafter, the identified target identification information and target information are reassigned to each slave bullet so that there is no missing target, and the reassigned target identification information and target information are transmitted to the slave bullet (S107).

2 is a configuration diagram for explaining a process of acquiring a target in the target detection apparatus according to an embodiment of the present invention.

The target detection apparatus of this embodiment schematically includes a target database 10 in which target information is recorded and stored, an optical device 20 for generating target information by acquiring and reconstructing an image, and an inertial measuring device 30 for measuring the posture of a guided missile do.

First, when an image is input to the optical device 20, an image is acquired through an image sensor (S201). In order to classify the target in the acquired image, the target and the background are separated, the feature value is extracted, the classification model is designed, and the learning and matching steps with the pre-learned model are performed.

At this time, in order to ensure excellent performance in target detection in various environments, it is necessary to extract key points. Feature point extraction is to find a feature location that can robustly detect a target when the image environment changes.

Thereafter, a two-dimensional target model that is invariant to environmental changes is generated based on the extracted key points, and the target is searched through the extracted key points and the generated target model (S203).

When the target is searched, comparison with target information stored in the target database 10 is performed (S205), and the target is determined through this (S207).

On the other hand, the angle of the image obtained through the posture information input from the inertia measurer 30 is estimated (S209). At this time, the angle of incidence of the target and the missile is calculated by estimating the error in the elevation angle, azimuth angle, and viewing angle.

Thereafter, the distance from the extracted feature point is calculated (S211), and the image is reconstructed using the previously calculated incident angle and distance as input conditions (S213).

Thereafter, the determined target information is vector-converted (S215), and image reconstruction information and target information are transmitted (S217).

3 is a flowchart sequentially illustrating a process of generating target vector data according to an embodiment of the present invention.

First of all, when multiple missiles are fired at the same time, one Master bullet is determined according to the priority, and the remaining bullets become slaves. Master bullets and slave bullets are set in advance in the ground operation equipment before launching the missile, and a unique ID is assigned to identify not only the master bullet but also a number of guided missiles.

When the image sensor unit of the optical device 20 generates an image in units of frames, the image preprocessor performs an image preprocessing process (S301). Preferably, the video image is generated in two frames.

Background and image are separated for target acquisition, and feature points are extracted for target classification robust to environmental changes. A two-dimensional target model that is invariant to environmental changes is generated through the extracted feature points.

Thereafter, a target exceeding a threshold value of a predetermined pixel or more is searched for in the image through the extracted feature points and the generated target model (S303).

When a target exceeding the target threshold is searched according to a pre-calculated equation, vector transformation is performed on the direction and speed of the target data (S305).

Thereafter, it is compared with the target data stored in the target database 10 to determine whether the target data matches the target data (S307).

The above process is repeated until all targets are detected (S309), and when all targets are detected, the target is determined (S311), and target vector data is generated (S313).

The generated target vector data (A) is transmitted to the master guided missile for image reconstruction (S315). Master bullet synthesizes target vector data (A) received from slave bullets.

4 is a flowchart sequentially illustrating a virtual battlefield data generation process according to an embodiment of the present invention, using the target vector data (A) generated through the process of FIG. 3 and sensor information collected from each guided missile. The process of generating two-dimensional virtual battlefield data will be described.

First, each guided missile may receive its own location information through an inertial measuring device or GPS (S401), and based on the received location information, a coordinate vector (B) of the slave projectiles is generated (S403).

In addition, each missile sensor (gyro, acceleration, angular velocity, etc.) information is collected and collected through an inertia meter (S405), and an incident angle of the missile is calculated through gyro transformation (S407).

A plane is constructed using the derived incident angle and bullet propagation direction information (S409), and a center point of the plane constructed with the coordinates of each bullet as the origin is set (S411).

In addition, the distance to the target is estimated using the previously received target vector data (A) and the incident angle and acceleration derived through the step S407 ( S413 ).

When the distance to the target is estimated, a distance vector between the targets is extracted based on the distance between the center point set in step S411 and the estimated target (S415).

After that, each bullet receives attitude information and position information from the inertial measurement device as in steps S401 and S403, converts the coordinate vectors of slave bullets, and virtual arrangement between the master bullet and slave bullets, and then the previously extracted distance vector (S415) ) to generate 2D virtual battlefield data C (S417). At this time, all the 2D virtual battlefield data (C) transmitted is data converted into vectors rather than images of all pixels, and by reducing the size of data, fast transmission without delay is possible, and stability can be maximized.

5 is a flowchart sequentially illustrating a process of simultaneously acquiring a plurality of targets according to an embodiment of the present invention.

First, when a plurality of guided missiles are simultaneously fired, one master bullet is set according to the priority of the guided missile, and the remaining bullets are set as slave bullets (S501). Master bullets are preset in ground operation equipment before launch, and the Master moves around the main strike point, and each Slave forms a formation with the Master in Central America.

Next, the coordinates of the master bullet are set as the origin in the virtual battlefield (S503), and the virtual battlefield arrangement for the master bullet is performed based on this (S505).

Thereafter, the bullet coordinate vectors B and the virtual battlefield data C obtained in FIG. 4 are received, and a plurality of two-dimensional virtual battlefields are overlapped and connected to each other (S507).

On the placed virtual battlefield, using the target vector data (A) obtained in FIG. 3, the bullet coordinate vectors (B) obtained in FIG. 4, and the virtual battlefield data (C), the targets based on the center point arranged, and converted back to vector data (S511).

The above process is repeatedly performed for all the acquired targets (S513), and when all the targets are placed, the targets placed on the virtual battlefield of the slave are moved to the virtual battlefield of the master and are deleted from the virtual battlefield of the slave.

That is, it is checked whether there is a target in the virtual battlefield fired by the slave (S515), and if there is a target (S517), the target is deleted from the virtual battlefield fired by the slave and moved to the virtual battlefield master (S519).

After checking the presence of targets in the virtual battlefield for all slave bullets, when all targets are moved to the virtual battlefield of the master bullet, a command to move each bullet to the target area is sent to all slave bullets (S521) ) to acquire all targets without undetected targets at the same time.

Through this process, all guided missiles can identify the target. In the master ammunition, reconfigure the battlefield and identify the target and deploy it to all slave ammunition. If there are no targets in your area or there are many important targets in other areas, you can send a strike request from the slave to another slave, and the slave who receives the request changes the target or moves to the target area.

6 and 7 are reference diagrams for explaining an image block allocation process and results for target acquisition in an actual battlefield environment according to an embodiment of the present invention.

In an actual battlefield environment, in order to disable multiple targets at the same time, as shown in FIG. 6 , images acquired from the optics mounted on each guided missile and generated target information are shared. Afterwards, the battlefield composed by the self-acquired image and target information is reconstructed by synthesizing it with information obtained from other guided missiles. In this case, the transmitted image is divided into blocks, and according to an embodiment of the present invention, the blocks may be allocated by dividing each missile by a radius of 500 m for each target. Preferably, the blocks may be allocated to overlap by 10±5% of the total area for ease of image reconstruction.

Referring to FIG. 7 , the optics calculates the distance from the center point of the reconstructed image to the target feature point to obtain the target position. Then, information about the virtual 2D battlefield and target is identified and meaningful data fields are reconstructed. Through this, it is possible to disable multiple targets at the same time without missing targets based on the target information obtained from each guided missile.

8 is a block diagram schematically illustrating the configuration of a target detection apparatus according to an embodiment of the present invention.

As shown, the target detection apparatus includes a sensor unit 10 , an image preprocessor 20 , an image processing unit 30 , a target acquisition unit 40 , a target database 50 , and a communication unit 60 .

The target database 50 stores the acquired target information, and the stored target information is used to compare and determine a target from the acquired image.

The sensor unit 10 includes an image sensor and an acceleration, angular velocity, gyro sensor, and the like capable of acquiring posture information of the guided missile. The image sensor may be an infrared sensor, a visible light sensor, or the like, and acquires an image including a target. In addition, the attitude information of the guided missile can be obtained through the acceleration, angular velocity, and gyro sensors.

The image preprocessor 20 performs a preprocessing process for extracting target information from the image acquired through the sensor unit 10 . The image pre-processing process includes image quality improvement, restoration, understanding, compression, and encoding processes, and through the pre-processing process, target vector data is generated and target information is transmitted to the image processing unit.

Specifically, the process of generating the target vector data is as follows. When an image is acquired through the image sensor 10, a two-dimensional target model is generated after extracting feature points by separating the target and the background from the acquired image. Thereafter, the target is searched for through the feature point and the target model, the target is determined by comparing it with target information stored in the target database, and target vector data is generated through the determined target direction and velocity information.

The image processing unit 30 reconstructs the image obtained from the sensor unit 10 based on the posture information of the guided missile obtained through the sensor unit 10 and the target information extracted through the image preprocessing unit 20 . Then, the image processing unit 30 estimates the distance to the target using the incident angle, the traveling direction, and the target information of the guided missile, sets the traveling direction of the guided missile as a central point, and converts the distance to the target into vector data to obtain an image create information

The target acquisition unit 40 searches for a target from the image reconstructed through the image processing unit 30 , compares it with target information in the target database 50 , and finally acquires the target.

Through the communication unit 60, target information and image information are received from the slave bullet. In addition, the slave bullets are rearranged to the plurality of targets identified in the 2D battlefield image reconstructed by the image processing unit 30 of the master bullet, and target information including the target ID is transmitted to the slave bullets through the communication unit 60 . Communication between guided missiles through the communication unit 60 according to an embodiment of the present invention may apply a beacon protocol.

On the other hand, the process of acquiring a target from the target detection device, generating target vector data and virtual battlefield data, acquiring multiple targets simultaneously, and arranging as slave bullets has been described in detail with reference to FIGS. 1 to 5 above, detailed description is omitted.

Even if all the components constituting the embodiment of the present invention described above are described as being combined or operated in combination, the present invention is not necessarily limited to this embodiment. That is, within the scope of the object of the present invention, all the components may operate by selectively combining one or more. In addition, although all the components may be implemented as one independent hardware, some or all of the components are selectively combined to perform some or all of the functions of the combined hardware in one or a plurality of hardware program modules It may be implemented as a computer program having In addition, such a computer program is stored in a computer readable media such as a USB memory, a CD disk, a flash memory, etc., read and executed by the computer, thereby implementing the embodiment of the present invention. The computer program recording medium may include a magnetic recording medium, an optical recording medium, a carrier wave medium, and the like.

In addition, all terms including technical or scientific terms have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs, unless otherwise defined in the detailed description. Commonly used terms such as terms defined in the dictionary should be interpreted as being consistent with the contextual meaning of the related art, and are not interpreted in an ideal or excessively formal meaning unless explicitly defined in the present invention.

The above description is merely illustrative of the technical idea of the present invention, and various modifications, changes, and substitutions are possible within the range that does not depart from the essential characteristics of the present invention by those of ordinary skill in the art to which the present invention pertains. will be. Accordingly, the embodiments disclosed in the present invention and the accompanying drawings are for explaining, not limiting, the technical spirit of the present invention, and the scope of the technical spirit of the present invention is not limited by these embodiments and the accompanying drawings. . The protection scope of the present invention should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

10: sensor unit
20: image preprocessor
30: image processing unit
40: target acquisition unit
50: target database
60: communication department

Claims (13)

A first step of acquiring an image through an image sensor, detecting a target by referring to a target database, and generating target information;
a second step of generating image information by reconstructing the acquired image with reference to the guided missile attitude information and position information measured from the sensor unit;
a third step of receiving a plurality of image information, target information, and coordinate vectors respectively generated from a plurality of adjacent missiles;
a fourth step of reconstructing a virtual two-dimensional full-length image by overlapping and linking the plurality of image information received in the third step with the image information generated in the second step;
A fifth step of identifying a plurality of targets in the virtual two-dimensional battlefield image with reference to the target information and assigning IDs so as to be respectively disposed on the plurality of guided missiles to classify the targets; and
and a sixth step of transmitting target information including identification information of the target and the ID to the plurality of guided missiles. According to claim 1,
The target information is a target detection method, characterized in that the vector data indicating the direction and speed of the target. According to claim 1,
The image information is two-dimensional virtual battlefield data converted into vector data by estimating the distance to the target using the incident angle, the direction of travel and the target information of the missile, and setting the center point. According to claim 1, wherein the first step,
acquiring an image through an image sensor;
generating a two-dimensional target model after extracting feature points by separating the target and the background from the acquired image;
determining a target by searching for a target through the feature point and the target model and comparing it with target information stored in a target database; and
Target detection method comprising the step of generating target vector data through the determined target direction and velocity information. According to claim 4, wherein the second step,
The method of claim 1, comprising: generating the bullet coordinate vector data and the battlefield image data by using the location information, the incident angle, and the traveling direction information of the guided missile. According to claim 1, wherein the second step,
A target detection method, characterized in that by referring to the location information of the guided missile, setting the moving direction as a central point and generating the image information. According to claim 6, wherein the fourth step,
Set the progress direction set with reference to the location information of the second step as the origin,
A target detection method characterized in that the plurality of image information received in the third step and the image information generated in the second step are superimposed and connected. a target database in which information about the target is stored;
a sensor unit that acquires an image including the posture information and the target of the guided missile;
an image preprocessor for performing a preprocessing process for extracting target information from the image acquired through the sensor unit and generating target information;
an image processing unit configured to reconstruct the image obtained from the sensor unit based on the posture information obtained through the sensor unit and target information extracted through the image preprocessor to generate image information; and
Target detection apparatus comprising a; target acquisition unit for obtaining a target by searching for a target from the image reconstructed through the image processing unit and comparing with target information of the target database. 9. The method of claim 8,
The target information is a target detection device, characterized in that the vector data indicating the direction and speed of the target. 9. The method of claim 8,
The image processing unit estimates the distance to the target using the incident angle, the traveling direction, and the target information of the guided missile, sets the traveling direction of the guided missile as a central point, and converts the distance to the target into vector data to generate the image information Target detection device, characterized in that. The method of claim 8, wherein the image preprocessor,
After separating the target and the background from the image acquired through the sensor unit to extract the feature point, a two-dimensional target model is generated, and the target is searched based on the feature point and the target model and compared with the target information stored in the target database. to determine the target, and to generate target information through the determined target direction and speed information. 9. The method of claim 8,
Target detection apparatus, characterized in that it further comprises a communication unit for receiving the target information and image information from the outside. The method of claim 12, wherein the image processing unit,
It receives a plurality of image information, target information, and coordinate vectors generated from a plurality of adjacent missiles through the communication unit, and superimposes and connects the plurality of received image information with the generated image information to obtain a virtual two-dimensional battlefield image. reconstructs, identifies a plurality of targets in the virtual two-dimensional battlefield image with reference to the target information, assigns IDs to be disposed on the plurality of guided missiles, respectively, and includes target information including identification information of the target and the ID Target detection device, characterized in that the transmission to the plurality of guided missiles through the communication unit.

Images