RISS 학술연구정보서비스

검색
다국어 입력

http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

변환된 중국어를 복사하여 사용하시면 됩니다.

예시)
  • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
  • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
닫기
    인기검색어 순위 펼치기

    RISS 인기검색어

      검색결과 좁혀 보기

      선택해제
      • 좁혀본 항목 보기순서

        • 원문유무
        • 원문제공처
        • 등재정보
        • 학술지명
        • 주제분류
        • 발행연도
        • 작성언어
        • 저자
          펼치기

      오늘 본 자료

      • 오늘 본 자료가 없습니다.
      더보기
      • 무료
      • 기관 내 무료
      • 유료
      • KCI등재

        드론 영상 기반 조난 선박 탐지를 위한해양 환경 시뮬레이션을 활용한 딥러닝 모델 개발

        오정효,이주희,전의익,이임평 대한원격탐사학회 2023 大韓遠隔探査學會誌 Vol.39 No.6

        In the context of maritime emergencies, the utilization of drones has rapidly increased,with a particular focus on their application in search and rescue operations. Deep learning modelsutilizing drone images for the rapid detection of distressed vessels and other maritime drift objectsare gaining attention. However, effective training of such models necessitates a substantial amount ofdiverse training data that considers various weather conditions and vessel states. The lack of such datacan lead to a degradation in the performance of trained models. This study aims to enhance theperformance of deep learning models for distress ship detection by developing a maritime environmentsimulator to augment the dataset. The simulator allows for the configuration of various weatherconditions, vessel states such as sinking or capsizing, and specifications and characteristics of dronesand sensors. Training the deep learning model with the dataset generated through simulation resultedin improved detection performance, including accuracy and recall, when compared to models trainedsolely on actual drone image datasets. In particular, the accuracy of distress ship detection in adverseweather conditions, such as rain or fog, increased by approximately 2–5%, with a significant reductionin the rate of undetected instances. These results demonstrate the practical and effective contributionof the developed simulator in simulating diverse scenarios for model training. Furthermore, the distressship detection deep learning model based on this approach is expected to be efficiently applied inmaritime search and rescue operations.

      • KCI등재

        무한물점용 줌 렌즈 광학계의 줌 궤적에 대한 해석적 계산법

        오정효,류재명,조재흥,Oh, Jeong Hyo,Ryu, Jae Myung,Jo, Jae Heung 한국광학회 2013 한국광학회지 Vol.24 No.3

        In case of the optical camera system with an infinite object distance, optical designs different from previous systems are required to speed up the auto-focus. As the number of lens groups is increased due to this, the conventional analytic method found it difficult to calculate the locus, and even the one-step advanced calculation method also had the trouble of taking a lot of time. In this paper, we suggested an analytic method for calculating the zoom loci by analyzing movement of one or two groups for situations corresponding to the given back focal length and effective focal length after taking a spline interpolation for each lens group. With this method, we would not only calculate the analytic zoom loci without iterations in every optical system without placing a limit on the group number at the zoom lens systems with the infinite object distance, but we would also show the utilities of this method through many examples. 무한물점으로 취급하는 카메라 광학계의 경우, 자동초점(auto-focus) 속도를 빠르게 하기 위해 기존 광학계와 다른 형태로 광학설계를 하게 된다. 이 때문에 군의 개수가 늘어나므로, 기존의 해석적인 방법으로는 궤적 계산이 어렵고, 또한 수치해석적인 방법은 시간이 많이 걸리는 단점이 있다. 본 논문에서는 각 군을 스플라인 보간을 한 뒤, 주어진 뒤정점초점거리와 유효초점거리를 만족하도록 1개 또는 2개 군의 이동량을 해석적으로 구해 줌 궤적을 계산하는 해석적인 방법을 제안하고 이를 유도한다. 이 방법은 무한물점용 줌 렌즈 광학계에서 군수의 제한 없이 모든 광학계에 대해 반복적인 계산없이 해석적인 궤적을 구할 수 있으며, 다양한 예제를 통하여 그 효용성을 보였다.

      • KCI등재

        반복사인격자에서 동시에 생기는 두 가지 무아레 무늬를 이용한 회전변위의 가시적 측정

        정연홍,오정효,조재흥,Jeong, Youn-Hong,Oh, Jeong-Hyo,Jo, Jae-Heung 한국광학회 2008 한국광학회지 Vol.19 No.4

        We present the precise visual measurement method of rotational displacements using two different moire fringes simultaneously generated by repeated sinusoidal gratings. We investigate the variation of moire fringes depending on rotational displacements through computer simulation and experiment using a rotator in detail. The moire fringes are composed of the wide linear fringe part with a long period and the narrow linear fringe part with a short period. These parts are superior to the angle detection of more than 12 degrees and less than 12 degree, respectively. Additionally, the method can be visually used in the determination of the rotational direction by observing the moire fringe's direction. 컴퓨터 전산모의와 회전자를 이용한 실험을 통하여 회전변위에 따른 반복사인격자 한 쌍이 만드는 무아레 무늬의 변화를 세밀하게 조사하여 반복사인격자가 겹쳐서 동시에 생기는 두 가지의 서로 다른 무아레 무늬를 사용하는 작은 회전변위를 측정하는 가시적 방법을 보여준다. 이 무아레 무늬는12도 이상의 큰 각도 측정에 유용한 장주기의 넓고 긴 직선무늬와 12도 이하의 작은 각도 측정에 유리한 좁고 짧은 복잡한 직선무늬로 이루어져 있다. 그리고 무아레 무늬의 회전방향에 따라 회전변위의 회전방향도 동시에 가시적으로 판별할 수 있다.

      • KCI등재

        Unified Analytic Calculation Method for Zoom Loci of Zoom Lens Systems with a Finite Object Distance

        유재명,오정효,조재흥 한국광학회 2014 Current Optics and Photonics Vol.18 No.2

        The number of lens groups in modern zoom camera systems is increased above that of conventional systems in order to improve the speed of the auto focus with the high quality image. As a result, it is difficult to calculate zoom loci using the conventional analytic method, and even the recent one-step advanced numerical calculation method is not optimal because of the time-consuming problem generated by the iteration method. In this paper, in order to solve this problem, we suggest a new unified analytic method for zoom lens loci with finite object distance including infinite object distance. This method is induced by systematically analyzing various distances between the object and other groups including the first lens group, for various situations corresponding to zooming equations of the finite lens systems after using a spline interpolation for each lens group. And we confirm the justification of the new method by using various zoom lens examples. By using this method, we can easily and quickly obtain the zoom lens loci not only without any calculation process of iteration but also without any limit on the group number and the object distance in every zoom lens system.

      연관 검색어 추천

      이 검색어로 많이 본 자료

      활용도 높은 자료

      해외이동버튼