• 한국군사과학기술학회지
• /
• 제15권2호
• /
• pp.169-176
• /
• 2012

GPS(Global Positioning System) is widely used for the position estimation of an aerial vehicle. However, GPS may not be available due to hostile jamming or strategic reasons. A vision-based position estimation method can be effective if GPS does not work properly. In mountainous areas without any man-made landmark, a horizon is a good feature for estimating the position of an aerial vehicle. In this paper, we present a new method to estimate the position of the aerial vehicle equipped with a forward-looking infrared camera. It is assumed that INS(Inertial Navigation System) provides the attitudes of an aerial vehicle and a camera. The horizon extracted from an infrared image is compared with horizon models generated from DEM(Digital Elevation Map). Because of a narrow field of view of the camera, two images with a different camera view are utilized to estimate a position. The algorithm is tested using real infrared images acquired on the ground. The experimental results show that the method can be used for estimating the position of an aerial vehicle.

• 한국군사과학기술학회지
• /
• 제21권2호
• /
• pp.133-140
• /
• 2018

In electronic warfare(EW), low probability of intercept(LPI) radar signal is a survival technique. Accordingly, identification techniques of the LPI radar waveform have became significant recently. In this paper, classification and extracting parameters techniques for 7 intrapulse modulated radar signals are introduced. We propose a technique of classifying intrapulse modulated radar signals using Convolutional Neural Network(CNN). The time-frequency image(TFI) obtained from Choi-William Distribution(CWD) is used as the input of CNN without extracting the extra feature of each intrapulse modulated radar signals. In addition a method to extract the intrapulse radar modulation parameters using binary image processing is introduced. We demonstrate the performance of the proposed intrapulse radar waveform identification system. Simulation results show that the classification system achieves a overall correct classification success rate of 90 % or better at SNR = -6 dB and the parameter extraction system has an overall error of less than 10 % at SNR of less than -4 dB.

• 한국군사과학기술학회지
• /
• 제13권5호
• /
• pp.894-902
• /
• 2010

This paper presents a vision-based robust off-road terrain classification method against environmental variation. As a supervised classification algorithm, we applied a neural network classifier using wavelet features extracted from wavelet transform of an image. In order to get over an effect of overall image feature variation, we adopted environment sensors and gathered the training parameters database according to environmental conditions. The robust terrain classification algorithm against environmental variation was implemented by choosing an optimal parameter using environmental information. The proposed algorithm was embedded on a processor board under the VxWorks real-time operating system. The processor board is containing four 1GHz 7448 PowerPC CPUs. In order to implement an optimal software architecture on which a distributed parallel processing is possible, we measured and analyzed the data delivery time between the CPUs. And the performance of the present algorithm was verified, comparing classification results using the real off-road images acquired under various environmental conditions in conformity with applied classifiers and features. Experiments show the robustness of the classification results on any environmental condition.

• 한국군사과학기술학회지
• /
• 제22권4호
• /
• pp.475-483
• /
• 2019

Although radar target signatures(RTS), such as range profiles have played an important role for target recognition in the X-band radar, they would be less effective when a target is designed to have low radar cross section(RCS). Recently, a number of research groups have conducted the studies on the RTS in the VHF-band where such targets can be better detected than in the X-band. However, there is a lack of work carried out on the mathematical description of the VHF-band RTS. In this paper, chirplet decomposition is employed for modeling of the VHF-band RTS and its performance is compared with that of existing scattering center model generally used for the X-band. In addition, the discriminative signal analysis is performed by chirplet parameterization of range profiles from in an ISAR image. Because the chirplet decomposition takes long computation time, its fast form is further proposed for enhanced practicality.

• 한국군사과학기술학회지
• /
• 제24권3호
• /
• pp.281-292
• /
• 2021

With the development of deep learning technology, researchers and technicians keep attempting to apply deep learning in various industrial and academic fields, including the defense. Most of these attempts assume that the data are balanced. In reality, since lots of the data are imbalanced, the classifier is not properly built and the model's performance can be low. Therefore, this study proposes cost-sensitive learning as a solution to the imbalance data problem of image classification in the defense field. In the proposed model, cost-sensitive learning is a method of giving a high weight on the cost function of a minority class. The results of cost-sensitive based model shows the test F1-score is higher when cost-sensitive learning is applied than general learning's through 160 experiments using submarine/non-submarine dataset and warship/non-warship dataset. Furthermore, statistical tests are conducted and the results are shown significantly.

• 한국군사과학기술학회지
• /
• 제24권1호
• /
• pp.12-21
• /
• 2021

For successful automatic target recognition(ATR) with synthetic aperture radar(SAR) imagery, SAR target images of the database should have the identical or highly similar resolution with those collected from SAR sensors. However, it is time-consuming or infeasible to construct the multiple databases with different resolutions depending on the operating SAR system. In this paper, an approach for resolution conversion of SAR target images is proposed based on conditional generative adversarial network(cGAN). First, a number of pairs consisting of SAR target images with two different resolutions are obtained via SAR simulation and then used to train the cGAN model. Finally, the model generates the SAR target image whose resolution is converted from the original one. The similarity analysis is performed to validate reliability of the generated images. The cGAN model is further applied to measured MSTAR SAR target images in order to estimate its potential for real application.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권11호
• /
• pp.521-528
• /
• 2021

군사 분야에서 사용 중인 기존 영상 판독 시스템은 판독관들이 직접 영상을 분석 및 식별하여 관련 내용을 보고서에 작성하고 전파하는 방식으로 진행되는데 이 과정에서 반복 작업이 빈번하여 업무 과부하가 발생한다. 본 논문에서는 이러한 문제를 해결하고자, 기존의 문장 단위로 동작하는 Seq2Seq 모델을 단어 단위로 동작할 수 있는 알고리즘을 제안하고, Attention 기법을 적용해 정확도를 향상시키고자 한다. 또한 Beam 탐색 기법을 응용하여 특정 지역의 과거 식별내용을 바탕으로 현재 식별 문장을 다양하게 추천하고자 한다. 실험을 통해 Beam 탐색 기법이 기존 Greedy 탐색 기법보다 효과적으로 문장을 추천하는 것을 확인하였고, Beam의 크기가 클 때 추천의 정확도가 높아지는 것을 확인하였다.

• 한국광학회지
• /
• 제31권6호
• /
• pp.314-320
• /
• 2020

적외선 영상 장비에 사용되는 광학계는 온도에 따른 굴절률의 변화가 심해 운용 온도 범위가 넓은 군용 적외선 영상장비에는 자동초점조절 기능이 필수적이다. 본 논문에서는 3중 배율의 적외선 영상 장비를 설계하고 해당 장비의 온도에 따른 굴절률 변화를 보상하기 위하여 온도 챔버에 영상 장비와 시준기를 설치하여 온도에 따른 렌즈 초점 이동량 변화를 측정하였다. 측정된 이동량을 활용하여 자동초점조절 기능을 구현하였으며 두 번의 온도 시험을 통해 -35~71℃의 넓은 운용 온도범위에서 상온의 MTF 성능과 동등한 수준의 분해능 성능의 영상을 확인하였다.

• 한국콘텐츠학회논문지
• /
• 제3권3호
• /
• pp.19-33
• /
• 2003

군사분야에서 컴퓨터 시뮬레이션의 활용은 이미 수십년전부터 이루어지고 있다. 컴퓨터 시뮬레이션을 통해서 실제전투자산을 가동하지 않고 실전과 같은 전투경험을 부여하고 있다. 이러한 시뮬레이션이 실제와 똑같은 환경을 구축하기 위해서는 페더레이트(federate)간의 연동(federation)이 네트워크 상에서 잘 수행되어야 한다. 이에 본 논문에서는 전장 데이터(이하 액티브 패킷)의 신속한 전달을 필요로 하는 긴급한 실제상황과 유사한 전장공간을 구축할 수 있도록 액티브네트워크 상에서의 동적기술(혹은 액티브 네트워크 기술)을 이용해 페더레이트(혹은 액티브 노드) 간의 효율적인 트래픽처리가 가능한 가상 전장 환경을 구성하고, 이에 대한 유효성을 모의실험을 통하여 검증하였다.

• 한국의류산업학회지
• /
• 제8권1호
• /
• pp.34-40
• /
• 2006

Fascism is a term that began to be used from the late 1930s, means an idea and a system that the strong power of the state intervenes or control people's life based on the argument that the existential value of individuals is found only in the total. Fascist looks, which resulted from World War I and II, had brought a new pattern in women's fashion inspired by men's military uniforms. Thus, the purpose of this study was to identify fascist fashion trends in the first half of the twentieth century and to infer various aesthetic values of fascism expressed in fascist fashion looks. The results of this study indicated that expressions of fascism reflected the current ideology of rebellion and appealed to the original national sentiment of the masses. Fascism occurred in response to the contradiction of capitalism and its general crisis had emerged as an ideology with the highest popularity symbolizing power and government during the first half of the twentieth century. It was expressed in military looks as self-centered nationalism and yearning for minorities. Second, fascist fashion looks were not only for political and sexual temptation with the image of power but also for the display of women's status and roles through the bold expression of sexual attractiveness. Finally, fascist fashion looks expressed medieval images praising the feudal age in imagination that contained heroism and at the same time achieved integration under strict social hierarchical order.