• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권2호
• /
• pp.837-856
• /
• 2016

Underwater image enhancement has received considerable attention in last decades, due to the nature of poor visibility and low contrast of underwater images. In this paper, we propose a new automatic underwater image enhancement algorithm, which combines nonsubsampled contourlet transform (NSCT) domain enhancement techniques with the mechanism of the human visual system (HVS). We apply the multiscale retinex algorithm based on the HVS into NSCT domain in order to eliminate the non-uniform illumination, and adopt the threshold denoising technique to suppress underwater noise. Our proposed algorithm incorporates the luminance masking and contrast masking characteristics of the HVS into NSCT domain to yield the new HVS-based NSCT. Moreover, we define two nonlinear mapping functions. The first one is used to manipulate the HVS-based NSCT contrast coefficients to enhance the edges. The second one is a gain function which modifies the lowpass subband coefficients to adjust the global dynamic range. As a result, our algorithm can achieve contrast enhancement, image denoising and edge sharpening automatically and simultaneously. Experimental results illustrate that our proposed algorithm has better enhancement performance than state-of-the-art algorithms both in subjective evaluation and quantitative assessment. In addition, our algorithm can automatically achieve underwater image enhancement without any parameter tuning.

• 드라이브 ㆍ 컨트롤
• /
• 제17권3호
• /
• pp.1-8
• /
• 2020

Recently, a special purpose machine with two manipulators and quadruped crawler system has been developed for rapid life-saving and initial restoration work at disaster sites. This special purpose machine provides the driver with various environmental recognition functions for accurate and rapid task determination. In particular, the human detection technology assists the driver in poor working conditions such as low-light, dust, water vapor, fog, rain, etc. to prevent secondary human accidents when moving and working. In this study, a human detection module is developed to be mounted on a special purpose machine. A thermal sensor and CCD camera were used to detect victims and nearby workers in response to the difficult environmental conditions present at disaster sites. The performance of various AI-based life detection algorithm were verified and then applied to the task of detecting various objects with different postures and exposure conditions. In addition, image visibility improvement technology was applied to further improve the accuracy of human detection.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제6권4호
• /
• pp.840-866
• /
• 2014

Visibility in underwater images is usually poor because of the attenuation of light in the water that causes low contrast and color variation. In this paper, a new approach for underwater image quality improvement is presented. The proposed method aims to improve underwater image contrast, increase image details, and reduce noise by applying a new method of using contrast stretching to produce two different images with different contrasts. The proposed method integrates the modification of the image histogram in two main color models, RGB and HSV. The histograms of the color channel in the RGB color model are modified and remapped to follow the Rayleigh distribution within certain ranges. The image is then converted to the HSV color model, and the S and V components are modified within a certain limit. Qualitative and quantitative analyses indicate that the proposed method outperforms other state-of-the-art methods in terms of contrast, details, and noise reduction. The image color also shows much improvement.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2010년도 춘계학술발표논문집 1부
• /
• pp.400-403
• /
• 2010

도로상의 안개로 인한 시정감소는 교통사고를 유발하는 주된 원인이므로 전방의 운전자에게 도로의 시정거리를 미리 알려주어 안전운행을 유도하기 위한 안개경고시스템은 도로의 안전관리를 위해 매우 중요한 요소이다. 우리는 CCTV 카메라 영상에서 도로상에 통행중인 차량의 이동영역이 시정에 따라 달라진다는 점에 착안하여 이동영역을 추출하고 이를 이용하여 가시거리를 계산하는 시정 측정 장치를 개발하고 있으며, 주간, 야간 등 날씨의 변화에 덜 민감하면서도 효과적이고 정확한 이동영역의 추출은 시정측정을 위해 매우 중요하다. 본 논문에서는 이동영역의 추출을 위해 영상대비를 이용하여 자동으로 임계치를 결정하는 방법을 제안하며, 결정된 임계치를 적용시킴으로써 프레임간의 차영상으로 부터 잡음이 효과적으로 제거될 수 있음을 보인다. 또한, 차영상을 일정시간 누적시키는 방법을 통해 효과적으로 차량의 이동영역이 추출 되는 것을 보이기 위해 실제 고속도로에서 촬영된 CCTV 영상을 이용하여 실험한 결과를 제시한다.

• 터널과지하공간
• /
• 제20권6호
• /
• pp.465-474
• /
• 2010

중규모 터널(연장 1 km 이내) 건설은 최근 매년 30% 이상의 증가율을 보이고 있으나 환기 및 방재시설 설치기준은 제정되어 있지 않은 상태라 장대터널을 대상으로 한 설치기준을 따르고 있다. 이에 따라 중규모터널 환기 및 방재시설의 최적화 노력이 요구되고 있다. 본 연구에서는 중규모 터널 내 20 MW 규모의 화재 시 발생하는 화재연 역류거리, 고온 열기류 확산범위, 가시거리 20 m 이하(상류) 구간분포, 임계풍속 확보여부, 대피시간 등을 CFD 분석을 통해 방재팬의 적정 초기 가동시간을 도출하여 방재시스템의 최적운전 방안의 제시를 목적으로 한다.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 가을 학술논문 발표대회
• /
• pp.145-146
• /
• 2022

The demand for a construction method capable of securing a safety environment and improving quality is increasing. There is a high risk of falling when working at a high place in an environment where it is difficult to secure visibility, such as an underground space, and there is a risk of falling if cement liquid waterproof materials are transferred to the top of the scaffold by manpower. In addition, when working on a high place in a poor environment, the quality uniformity of the upper part of the wall is deteriorated. In addition, as waterproof technicians gradually age and decrease, it is difficult to secure them, so it is urgent to prepare countermeasures against the shortage of waterproof technicians. Therefore, the purpose of this study is to develop cement liquid waterproof spouting construction equipment that can secure uniform quality of construction areas to prevent accidents and ensure safety of workers, improve work efficiency and quality due to improvement of work environment. The adhesion performance of the cement liquid waterproof material could be improved by about 20% in accordance with the use of the equipment.

• 한국대기환경학회지
• /
• 제20권5호
• /
• pp.697-711
• /
• 2004

Severe haze, mist, and fog phenomena occurred in the central part of Korea during 15~25 May 2003 resulted in poor visibility and air quality. When these phenomena occurred, Korean peninsula was under the effects of anticyclone. The atmosphere was stable, and wind speed was so weak. Under this meteorological conditions, air quality was worse and worse. The characteristics of aerosol in Seoul, Incheon, and Gosan (Jeju) during this period are investigated from the $PM_{10}$. TSP concentrations and aerosol number concentrations. Concentrations of $PM_{10}$ and TSP measured at KMA increased upto 176 and 230 J.${\mu}g/m^3$ on 22 May 2003, respectively. Aerosol number concentrations of size range from 0.82 to 6.06 ${\mu}m$ increased in Seoul on 17, 19, and 21~24 May 2003, and the concentrations of $NO_2$ and $SO_2$had maximum value of 0.165 ppm at Gwanak Mt. and 0.036 ppm at Guro-dong on 23 May 2003, respectively. Result from analysis on heavy metal elements showed high concentrations of Zn, Pb, Cr, Ni, Cu, and Cd during 20~24 May 2003. This event is examined by comprehensive analyses of synoptic weather conditions, satellite images, concentrations of suspended particles and air pollutants, and heavy metal elements.

• 대한치과보존학회:학술대회논문집
• /
• 대한치과보존학회 2002년도 추계학술대회
• /
• pp.721-721
• /
• 2002

For about half a century. dental implants made of titanium have developed as a method of restoration for the tooth loss. In these days. the titanium implants seem to be considered as the alternative for the conventional prosthodontics. But its hard to say that the titanium implants are superior to the treatments that preserve the natural tooth. As this is a general opinion among dentists. the implant will not be able to be the alternative for all the prosthetic treatments. Clinically, there are many causes for extracting tooth. The severe destruction of the tooth structure or periodontal diseases leads to inevitable tooth extraction. When the complete cure is doubtful because of narrow intraoral visibility and improper accessibility in approaching to the tooth and periodontal lesion, we. clinicians often inevitably extract tooth. Passive treatments like conventional restoration, curettage or surgical flap cant be the perfect treatments for the tooth that has subgingival root caries or severe periodontal diseases involved furcation. Many clinicians might have been forced to pull out the relatively healthy tooth by the difficulties of approaching to the lesions and poor prognosis. Though the intentional tooth replantation is performed sometimes. as it doesnt have enough scientific foundation. it has not been considered as a popular treatment method yet. I have been felt keenly the necessity of positive tooth preservation, so I have been attempting the treatment that has new concept. calling Natural Tooth Implantation (NTI) clinically. NTI differs from the tooth replantation in the goal for the treatment and biological healing process. Now. I confirm that NT! is a very positive and valid method of tooth preservation. Like you can get from the name. NTI is the dental implant procedure using natural teeth and similar to the healing process of the titanium implants in many aspects. I have been using biocompatible composite resin. DRM. with NTI and got affirmative clinical results from that. So I would like to introduce.roduce.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제5권10호
• /
• pp.331-338
• /
• 2016

본 논문에서는 모션 센서를 이용한 군대 수신호 전송 시스템을 제안한다. 제안 시스템은 분대장 디바이스와 분대원 디바이스, 서버로 구성된다. 분대장 디바이스와 분대원 디바이스는 마이크로 아두이노와 가속도 센서, 자이로스코프 센서로 구현되었으며, 서버는 라즈베리파이3을 사용하여 구현되었다. 분대장 디바이스와 분대원 디바이스는 밴드 형태로 제작되었기 때문에 가볍고 휴대성이 좋다. 또한, 제안 시스템은 시야가 확보되지 않는 상황에서 진동을 통해 수신호를 전송할 수 있다. 제안 시스템에서 구현된 디바이스는 4가지의 수신호를 인식할 수 있으며, 실험을 통해 88.82%의 인식 성공률을 보였다. 본 연구의 결과물을 통해 군 작전의 효율성과 병사의 생존율을 높일 것을 기대한다.

• 전자공학회논문지
• /
• 제51권5호
• /
• pp.168-176
• /
• 2014

영상 시퀀스로부터 움직이는 객체의 검출은 비디오 감시, 교통 모니터링 및 분석, 사람 검출 및 추적 등에서 가장 기본적이며 중요한 분야이다. 안개와 같은 환경적 요인에 의하여 화질이 저하된 영상 속에서 움직이는 객체를 검출하는 일은 매우 어렵다. 특히, 안개는 주변 물체의 색상을 모두 비슷하게 만들고 채도를 떨어뜨려 배경으로부터 객체를 구별하기 힘들게 만든다. 이런 이유로 안개 영상 속에서 객체 검출 성능은 매우 낮으며 신뢰할 수 없는 결과를 나타내고 있다. 본 논문은 안개와 같은 환경적 요인을 제거하고 객체의 검출 성능을 높이기 위한 방법으로 안개 지수를 기반으로 안개 유무를 판단하고, Dark Channel Prior을 이용하여 안개 영상의 전달량을 추정하고 안개가 제거된 영상으로 복원하였으며 가우시안 혼합 모델을 이용한 배경 차분 방법을 이용하여 객체를 검출하였다. 그리고 제안된 방법의 성능을 비교하기 위해 안개 제거 전과 후의 영상에 대한 Recall 과 Precision을 측정하여 안개 제거에 따른 성능 향상 정도를 수치화하여 비교하였다. 결과적으로 안개 제거 후 영상의 가시성이 매우 향상되었으며 객체 검출 성능이 매우 향상됨을 알 수 있었다.