• 제목/요약/키워드: Synthetic Infrared Image

검색결과 11건 처리시간 0.026초

동아시아 표준 대기가 합성 적외선 영상에 미치는 효과 (Effect of the East Asian Reference Atmosphere on a Synthetic Infrared Image)

  • 신종진
    • 한국군사과학기술학회지
    • /
    • 제9권4호
    • /
    • pp.97-103
    • /
    • 2006
  • A synthetic infrared image can be effectively utilized in various fields such as the recognition and tracking of targets as long as its quality is good enough to reflect the real situations. One way to improve its quality is to use the reference atmosphere which best describes atmospheric properties of regional areas. The east asian reference atmosphere has been developed to represent atmospheric properties of the east asia including Korean peninsula. However, few research has been conducted to examine the effects of this east asian reference atmosphere on the modeling and simulation. In this regard, this paper analyzes the effects of the east asian reference atmosphere on a synthetic infrared image. The research compares the atmospheric transmittance, the surface temperature, and the radiance obtained by using the east asian reference atmosphere with those of the midlatitude reference atmosphere which has been widely applied in the east asia. The results show that the differences of the atmospheric transmittance, the surface temperature, and the radiance between the east asian reference atmosphere and the midlatitude reference atmosphere are significant especially during the daytime. Therefore, it is recommended to apply the east asian reference atmosphere for generating a synthetic infrared image with targets in the east asia.

SSIM 목적 함수와 CycleGAN을 이용한 적외선 이미지 데이터셋 생성 기법 연구 (Synthetic Infra-Red Image Dataset Generation by CycleGAN based on SSIM Loss Function)

  • 이하늘;이현재
    • 한국군사과학기술학회지
    • /
    • 제25권5호
    • /
    • pp.476-486
    • /
    • 2022
  • Synthetic dynamic infrared image generation from the given virtual environment is being the primary goal to simulate the output of the infra-red(IR) camera installed on a vehicle to evaluate the control algorithm for various search & reconnaissance missions. Due to the difficulty to obtain actual IR data in complex environments, Artificial intelligence(AI) has been used recently in the field of image data generation. In this paper, CycleGAN technique is applied to obtain a more realistic synthetic IR image. We added the Structural Similarity Index Measure(SSIM) loss function to the L1 loss function to generate a more realistic synthetic IR image when the CycleGAN image is generated. From the simulation, it is applicable to the guided-missile flight simulation tests by using the synthetic infrared image generated by the proposed technique.

실제 배경과 표적모델의 적외선 영상 합성 (Infrared Image Synthesis of Real Background and Target Model)

  • 안상호;김영춘;김기홍
    • 한국군사과학기술학회지
    • /
    • 제16권2호
    • /
    • pp.207-213
    • /
    • 2013
  • An infrared image synthetic method is proposed for infrared system simulation. The synthesis image uses a background IR image captured from real scene and a target IR modeling image. The radiances related with maximum and minimum temperatures of the background and target images are calculated from the Planck's blackbody equation. Based on them, the background and target images are compensated and synthesized. The proposed method is simulated and the IR target images are generated by RadThermIR software.

국방용 합성이미지 데이터셋 생성을 위한 대립훈련신경망 기술 적용 연구 (Synthetic Image Dataset Generation for Defense using Generative Adversarial Networks)

  • 양훈민
    • 한국군사과학기술학회지
    • /
    • 제22권1호
    • /
    • pp.49-59
    • /
    • 2019
  • Generative adversarial networks(GANs) have received great attention in the machine learning field for their capacity to model high-dimensional and complex data distribution implicitly and generate new data samples from the model distribution. This paper investigates the model training methodology, architecture, and various applications of generative adversarial networks. Experimental evaluation is also conducted for generating synthetic image dataset for defense using two types of GANs. The first one is for military image generation utilizing the deep convolutional generative adversarial networks(DCGAN). The other is for visible-to-infrared image translation utilizing the cycle-consistent generative adversarial networks(CycleGAN). Each model can yield a great diversity of high-fidelity synthetic images compared to training ones. This result opens up the possibility of using inexpensive synthetic images for training neural networks while avoiding the enormous expense of collecting large amounts of hand-annotated real dataset.

코팅된 무색 합성 모이사나이트의 특징 (Characterization of coated colorless synthetic moissanite)

  • 최현민;김영출;장한수;석정원
    • 한국결정성장학회지
    • /
    • 제32권1호
    • /
    • pp.7-11
    • /
    • 2022
  • 한미보석감정원은 최근에 5개의 투명한 합성 모이사나이트를 검사했다. 그 샘플들은 라운드 브릴리언트 컷의 무색, 핑크, 황색, 청색, 적색 컬러와 0.93~0.96 ct 중량을 가지고 있었다. FT-IR과 Raman 분석 결과 합성 모이사나이트임을 확인하였고, 확대검사 결과 무색을 제외한 나머지 샘플에서 코팅의 흔적이 발견되었다. EDXRF 분석 결과 무색 샘플을 제외한 모든 샘플의 코팅부분에서 Ca, Ti, Co의 미량원소가 검출되었다. 무색 샘플의 Raman 분석에서 탄소 원자의 sp3 bonding에 의해 생성되는 1332 cm-1 또는 graphite와 관련된 sp2 bonding에 의해 생성되는 ~1550 cm-1는 발견되지 않았다. 무색 샘플의 SEM 이미지에서도 코팅의 흔적은 발견되지 않았으나, TEM 이미지에서 3~8 nm의 코팅층의 존재가 발견됐다. EDX line 프로파일과 EDX elements map을 통해 무색 샘플의 코팅층을 구성하는 원소는 C, Si, O로 추정된다.

유도무기의 비행시험 결과 예측 및 분석을 위한 현장 영상 기반 시뮬레이션 기법 연구 (Study on On-Sight Image-Based Simulation Method for Predicting and Analyzing Flight Test Results of a Missile)

  • 정동길;박진서;이종희;손성한
    • 한국시뮬레이션학회논문지
    • /
    • 제28권3호
    • /
    • pp.41-48
    • /
    • 2019
  • 현대전에서 중시되는 부수피해 최소화를 위한 정밀타격 유도무기에는 적외선 영상탐색기가 주로 적용되는데, 고가의 적외선 센서를 탑재한 일회성 유도무기의 성능평가에는 많은 비용이 소모되게 된다. 이러한 비용 소모를 최소화하기 위해 시뮬레이션 기법을 통해 유도무기의 성능 예측을 수행하는데, 합성 적외선 영상을 적용한 시뮬레이션 기법이 대표적이다. 하지만 합성영상 적용 기법은 실제 영상과의 특성 차 및 다양한 환경 조건에 따라 변화하는 영상의 특성을 모두 고려하기 힘들다는 제한 사항을 가진다. 본 논문에서는 기존의 시뮬레이션 제한 사항을 보완하기 위한 계측 영상 기반 시뮬레이션 기법을 제안한다. 유도탄 발사 전에 획득되는 영상은 표적의 대조비 또는 온도차 등을 확인하여 영상 추적기의 성능발휘 조건 판단 목적으로만 적용되어 왔으나, 낮은 해상도 및 정보량 부족으로 통합 비행 시뮬레이션에 적용되는 시도조차 없었다. 하지만 본 논문에 기술한 연구를 통하여 현장 계측 영상을 적용한 통합 비행 시뮬레이션은 초기, 중기 비행 간의 유도탄 비행 성능을 상당히 유사하게 예측할 수 있으며 비행시험 결과 분석에 유용하게 활용할 수 있음을 확인하였다.

SAR Remote Sensing Technology Development and Application in China

  • Jing, Li
    • 대한원격탐사학회:학술대회논문집
    • /
    • 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
    • /
    • pp.448-453
    • /
    • 2002
  • Remote sensing technology is one of the most powerful tools for human to know the nature and their living environment. However, before microwave remote sensing was developed and applied, remote sensing application was limited strongly by weather and time. Microwave remote sensing technology solves the problem. It makes us to have the capability to acquire information at all time of the day and under all weather condition, and make remote sensing technology be used in more wider area. Microwave remote sensing system include mainly Synthetic Aperture Radar (SAR), Microwave Radiometer, Microwave Scatterometer, and Altimeter (ALT). As SAR can acquire image whose spatial resolution is similar with visible and infrared image, it is paying much attention to and playing a more and more important role in earth observation. In recent year, the development of new SAR technology (multi-band and multi-polarization technology, InSAR technology, D-InSAR technology, and so on) makes SAR remote sensing go to an new stage, and its application area become more and more widely. The first Synthetic Aperture Radar (SAR) in the world appeared in 1960. After that, SAR and its application all developed very fast. Some radar satellites launched and run (include Seasat-A in 1978, ERS-1 in 1991, JERS-1 in 1992, Radarsat in 1995, and so on) promote SAR research and application in world greatly. China began to develop its SAR sensor and research SAR application in 1970s. After more than 30 years' research, it get some important development in sensor development data processing method, and application. Some operational systems have been used and play an important role. This paper will introduce the development of SAR technology and its application in China.

  • PDF

연안 해양기상(해상풍, 수온) 관측을 위한 항공기 원격탐사 시스템 (Development of Airborne Remote Sensing System for Monitoring Marine Meteorology (Sea Surface Wind and Temperature))

  • 김덕진;조양기;강기묵;김진우;김승희
    • 한국해양학회지:바다
    • /
    • 제18권1호
    • /
    • pp.32-39
    • /
    • 2013
  • 인공위성은 넓은 지역에 대한 전 세계의 정보를 획득하는데 유용하지만, 좁은 지역에 대한 적시적소에 촬영하는 데는 한계가 있다. 이러한 단점을 극복하기 위하여 본 연구에서는 항공기 원격탐사 시스템을 구축하였다. 항공기 원격탐사시스템은 SAR센서와 열적외선 센서로 구성되어 있으며, 획득된 자료의 방사 및 기사보정을 위하여 GPS, IMU, 온도/습도계 등도 설치하였다. SAR영상은 표면 거칠기에 따라 민감하게 반응하여 밝기 값이 달라지게 되며, 해양에서는 바람에 의해 쉽게 생성 되는 표면 장력파의 진폭이 이러한 표면 거칠기를 야기한다. 따라서 정량화된 SAR의 후방산란과 해상풍 사이의 관계식을 통해 해상풍 추출이 가능하다. 한편, 열적외선 센서는 물체의 온도를 측정하는데 유용하며, 물체와 센서 사이의 대기에 의한 효과를 보정한 후 수온 추출이 이루어진다. 이 두 센서를 탑재한 항공기로 서해안 일대를 4차례 시험비행을 수행하였으며, 이로부터 획득된 SAR 및 열적외선 영상의 품질이 연안환경 모니터링 및 해양기상 자료 추출에 충분함을 보여주었다.

BMVT-M을 이용한 IR 및 SAR 융합기반 지상표적 탐지 (IR and SAR Sensor Fusion based Target Detection using BMVT-M)

  • 임윤지;김태훈;김성호;송우진;김경태;김소현
    • 제어로봇시스템학회논문지
    • /
    • 제21권11호
    • /
    • pp.1017-1026
    • /
    • 2015
  • Infrared (IR) target detection is one of the key technologies in Automatic Target Detection/Recognition (ATD/R) for military applications. However, IR sensors have limitations due to the weather sensitivity and atmospheric effects. In recent years, sensor information fusion study is an active research topic to overcome these limitations. SAR sensor is adopted to sensor fusion, because SAR is robust to various weather conditions. In this paper, a Boolean Map Visual Theory-Morphology (BMVT-M) method is proposed to detect targets in SAR and IR images. Moreover, we suggest the IR and SAR image registration and decision level fusion algorithm. The experimental results using OKTAL-SE synthetic images validate the feasibility of sensor fusion-based target detection.

Research on the relationship between the thermal characteristics and the type of land cover in Beijing urban area by ASTER data

  • Zhu, QiJiang;Zhang, Xin;Bai, Xianghua
    • 대한원격탐사학회:학술대회논문집
    • /
    • 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
    • /
    • pp.277-279
    • /
    • 2003
  • The study utilizes remote sensing as the main monitoring means. With different spatial high-resolution, multichannel ASTER remote sensing image as the main information in Beijing city zone; with regional border and statistical data as auxiliary factor a study between the thermal space distribution character and the underground medium is analyzed based on the GIS logical algorithm and synthetic analysis technology. Results show thermal forming mechanism and the rule of distribution is mainly related to the underground medium and the change of the city distribution. Different underground medium has different degree and intensity influence on the thermal space distribution. Furthermore, urban greenbelt and water areas can reduce the thermal effect and large-scale greenbelt creates green island effect. In addition, Road net, residential area, population density, heat resources and so on have some positive effect on the thermal distribution, which increase the local temperature and intensity on the other hand. It is important to study the thermal distribution and its related factors, which contributes to the plan, construction and development of the city.

  • PDF