• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1442-1445
• /
• 2015

본 논문은 SAR 영상에서 객체를 추출하는 새로운 방법으로 특징점 기반 분할 히스토그램 기법을 제안한다. 제안하는 방법은 영상 히스토그램에서 객체로 추정될 수 있는 영역을 세밀하게 추출하기 위해 영상에서 특징점을 추출한 후, 특징점의 밝기를 기준으로 히스토그램을 분할한다. 분할 히스토그램이 배경과 객체 성분을 모두 포함하고 있을 경우 해당 영역의 혼합 확률밀도함수가 교차되는 임계점을 계산한다. 계산된 임계점을 기준으로 현재 영역이 전체 영상에서 차지하는 비율을 비교하여 배경과 객체 여부를 판단한다. 제안하는 방법은 무인 감시 정찰 시스템 등 다양한 응용 기술에 활용될 수 있을 것으로 기대한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.507-509
• /
• 2023

본 논문에서는 DSP (Digital Signal Processing)를 이용한 차량용 레이다 수평안정화장치 구동 전략을 제안한다. 지대공 유도 미사일용 차량용 레이다는 전방향으로 일정 속도로 회전하며 감시정찰 임무를 수행한다. 수평안정화장치는 4세트의 수평구동모듈을 이용하여 차량 플랫폼의 수평을 유지하여 레이다의 안정적인 회전을 가능하게 한다. 이를 실시간으로 구현하기 위해 임베디드시스템인 DSP를 적용하여 경사도를 측정하고, 구동모듈에 구동 명령을 인가하여 수평을 유지한다. 수평구동모터는 감속기를 통하여 모터 토크를 증가시켜 수평 안정 동작을 수행한다. 본 논문에서는 수평구동모듈 1세트를 모델링하여 수평안정화장치를 축소 구현한다. 제안하는 구동 전략의 유효성은 시뮬레이션으로 입증한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.913-916
• /
• 2008

다중 센서 데이터 융합(Multi-Sensor Data Fusion)에 기반하여 자율관리 기능을 갖는 상황인식시스템에 대해 연구하였다. 다양한 형태의 센서들이 대규모의 네트워크로 연결된 환경에서 센서로부터 실시간으로 입력되는 데이터들을 융합하여 상황인식처리를 수행하는 시스템으로 노드에 설치된 소프트웨어 콤포넌트의 이상 유무를 자동 감지하고 치료하는 자율관리(Autonomic management) 기능을 갖는다. 제안한 시스템은 유비쿼터스 및 국방 무기체계의 감시·정찰, 지능형 자율 로봇, 지능형 자동차 등 다양한 상황인식 시스템에 적용가능하다.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.3
• /
• pp.99-106
• /
• 2018

In the process of acquiring information through the cyber ISR (Intelligence Surveillance Reconnaissance) and research into the agent to help decision-making, periodic communication between the C&C (Command and Control) server and the agent may not be possible. In this case, we have studied how to effectively surveillance and reconnaissance. Due to the network configuration, agents planted on infiltrated computers can not communicate seamlessly with C&C servers. In this case, the agent continues to collect data continuously, and in order to analyze the collected data within a short time in When communication is possible with the C&C server, it can utilize limited resources and time to continue its mission without being discovered. This research shows the superiority of incremental learning method over batch method through experiments. At an experiment with the restricted memory of 500 mega bytes, incremental learning method shows 10 times decrease in learning time. But at an experiment with the reuse of incorrectly classified data, the required time for relearn takes twice more.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.63-66
• /
• 2019

Recently, as the technology of drones develops, a malicious attack using a drones becomes a problem, and an anti-drone technology for detecting an attack dron for a malicious attack is required. However, currently used drone detection systems are expensive and require a lot of manpower. Therefore, in this paper, we propose an anti - drone method using the analysis and algorithms of the anti - drone that can monitor the attack drones. In this paper, we identify and detect attack drones using sniffing, and propose capture and deception algorithm through spoofing using current GPS based detection system.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.4
• /
• pp.219-228
• /
• 2013

The surveillance imaging equipments are functioning to observe the shape of the target in real time or to measure its location precisely. The roles of such equipments are becoming more important in today's weapon systems.The aforementioned imaging equipments can be classified based on the modes of operations such as fixed, installed on cars, or composite of those. Also, according to different concepts of sensor operation, a separate type uses independent housing for each sensor whereas in a composite type a set of multiple sensors are housed into a unit altogether. The sensors in general have magnetism, thereby introducing the possible negative effects, particularly in the composite types, in locating the reference position, which is carried out by the digital compass. The use of shielding material/housing could be an option but results in increased weight and reduced portability, restricting its use in composite type equipments. As such, the objective of this paper is to study on how to reduce such magnetic effects on the position location. To do so, in the absence of magnetic shielding, a variety of sensor positions were first modeled. By combing the result with the fact that the functions of PAN & Tilt are used in the equipments, a new position location algorithm is proposed. The use of the new algorithm can automate the position location process as compared to the manual process of the existing approach. In the algorithm developed, twelve locations are measured in connection with both the azimuth and elevation angles in comparison to the six locations alone around the azimuth angle. As a result, it turns out that the measurement range has been widened but the measurement time reduced. Also, note that the effect of errors the operators may make during measurement could be reduced.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.11
• /
• pp.51-59
• /
• 2018

The Multi-Mission Unmanned Surface Vehicle(MMUSV), which is manufactured using glass Fiber Reinforced Plastic(FRP) material, is designed to perform a surveillance and reconnaissance on the sea. Various navigation sensors, such as RADAR, RIDAR, camera, are mounted on a mast to perform an autonomous navigation. And a dummy gun is mounted on the deck of the MMUSV for a target tracking and disposal. It is necessary to analyze a strength for structures mounted on the deck because the MMUSV performs missions under a severe sea state. In this paper, a strength analysis of the mast structure is performed on static loads and lateral external loads to verify an adequacy of the designed mast through a series of simulations. Based on the results of captive model tests, a strength analysis for a heave motion of the mast structure is conducted using a simulation tool. Also a simulation and fatigue test for a mounting part between the MMUSV and the dummy gun are performed using a specimen. The simulation and test results are represented that a structure of the mast and mounting part of the dummy gun are appropriately designed.he impact amount are performed through simulation and experiments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.538-540
• /
• 2021

In this paper, we proposed a smart target detection system that detects and recognizes a designated target to provide relative motion information when performing a target detection mission of a drone. The proposed system focused on developing an algorithm that can secure adequate accuracy (i.e. mAP, IoU) and high real-time at the same time. The proposed system showed an accuracy of close to 1.0 after 100k learning of the Google Inception V2 deep learning model, and the inference speed was about 60-80[Hz] when using a high-performance laptop based on the real-time performance Nvidia GTX 2070 Max-Q. The proposed smart target detection system will be operated like a drone and will be helpful in successfully performing surveillance and reconnaissance missions by automatically recognizing the target using computer image processing and following the target.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.1-8
• /
• 2023

This paper presents the control strategy of Auto-leveling equipment (ALE) of Multi-function radar (MFR) for vehicle using Embedded System. MFR implements surveillance patrol missions such as surface-to-air missiles and fighters with constant rotation. ALE consists of 4 Auto-leveling modules (ALM) and retains the stability with maintaining level. The gradient of vehicle can be measured and controlled by embedded systems. This paper contributes for improvement the system design with the ALM 1 set modeling. The validity of the modeling is verified using MATLAB/Simulink.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.505-506
• /
• 2023

본 논문은 임베디드시스템을 적용한 대용량 고부하 레이다 플랫폼의 구동 제어 방안을 제안한다. 군사적 방어 목적용 지대공 유도 미사일 시스템의 구성품인 다기능 레이다 시스템은 고중량의 안테나를 구동해야하는 대용량 고부하 레이다 구동 플랫폼이 필수이다. 이 다기능 레이다 시스템은 360도 방위각 전방향을 일정한 속도로 방위각 회전하며 감시정찰 및 방어 임무를 수행한다. 여기서 대부하 레이다 구동 플랫폼은 방위각회전 구동장치를 이용하여 일정한 속도로 360도 방위각 방향으로 안정적인 회전을 가능하도록 구동 제어한다. 본 구동 제어를 실시간으로 구현하기 위해 임베디드시스템인 DSP(Digital Signal Processor)가 포함된 제어모듈은 구동모듈에 회전구동 명령을 인가하여 일정한 회전각속도로 구동하도록 회전구동 모터를 실시간 제어한다. 고부하 레이다 플랫폼은 직구동모터타입의 회전구동모터, 회전체에 신호와 전원을 공급하기 위한 회전슬립링, 회전체의 회전각도를 측정하기 위한 회전센서로 구성된 방위각회전구동장치와 전체 전원을 공급받아 사용 목적에 맞게 변환하여 공급하는 전원모듈, 구동모터에 구동전원을 공급하기 위한 구동모듈, 회전구동 명령에 따라 구동제어하기 위한 제어모듈로 구성된 제어장치로 구분된다. 본 논문에서는 대부하 레이다 구동 플랫폼을 시뮬레이션 모델링으로 구현하고 제안하는 구동 제어 방안은 구동제어시뮬레이션으로 검증한다.