• 대한원격탐사학회지
• /
• 제15권4호
• /
• pp.357-365
• /
• 1999

The optical sensors of Electro-Optical Camera (EOC) and Ocean Scanning Multi-spectral Imager (OSMI) aboard the KOrea Multi-Purpose SATellite (KOMPSAT) will be placed in a sun synchronous orbit in late 1999. The EOC and OSMI sensors are expected to produce the land mapping imagery of Korean territory and the ocean color imagery of world oceans, respectively. Utilization of the EOC and OSMI data would encompass the various fields of science and technology such as land mapping, land use and development, flood monitoring, biological oceanography, fishery, and environmental monitoring. Readiness of data support for user community is thus essential to the success of the KOMPSAT program. As a part of testing such readiness prior to the KOMPSAT launch, we have performed the preliminary acceptance test for the KOMPSAT data processing system using the simulated EOC and OSMI data sets. The purpose of this paper is to demonstrate the readiness of the KOMPSAT data processing system, and to help data users understand how the KOMPSAT EOC and OSMI data are processed, archived, and provided. Test results demonstrate that all requirements described in the data processing specification have been met, and that the image integrity is maintained for all products. It is however noted that since the product accuracy is limited by the simulated sensor data, any quantitative assessment of image products can not be made until actual KOMPSAT images will be acquired.

• 대한원격탐사학회지
• /
• 제26권5호
• /
• pp.537-547
• /
• 2010

FPAR는 다양한 육상 생태계 모텔에서 중요한 입력변수로 사용된다. 이 때문에 다양한 global product의 형태로 제공되고 있다. 하지만 한반도를 영역으로 하는 연구에 이를 바로 적용 시 오차가 발생할 수 있고, 이것은 위성자료를 이용한 지면 정보 산출에 있어서 직접적인 오차요인이 된다. 따라서 본 연구에서는 Terra/MODIS와 SPOT/VEGETATION 그리고 ECOCLIMAP 자료를 이용해 한반도에 최적화된 FPAR를 산출 하였고, 또한 기존에 사용하였던 LAI와의 관계식을 사용하지 않고, SPOT/VGT NDVI 로부터 계산된 FVC (Fraction Vegetation Cover)를 직접 이용하여 FPAR를 산출 하였다. 이를 위해 식생지수의 선형/비선형 관계를 이용하여 구하는 경험적인 방법을 적용하여 회귀분석을 수행한 결과 cropland와 forest에서 각각 결정계수 (Coefficient of Determination, $R^2$)가 0.9039. 0.7901으로 정확도가 높은 관계식을 도출해내었다. 최종적으로 Reference FPAR 자료와의 비교 분석을 통해 본 연구에서 산출된 FPAR가 전반적인 패턴을 잘 표현하면서 불규칙하게 발생하던 노이즈 또한 보정된 것을 확인 할 수 있었다. 이렇게 한반도에 최적화된 입력변수의 사용은 산출물의 정확도뿐만 아니라 연구의 질 향상에도 도움을 줄 것으로 사료된다.

• 대한원격탐사학회지
• /
• 제35권5_2호
• /
• pp.861-871
• /
• 2019

Landsat 위성영상은 재난 피해 지역에 대해 주기적이며 광역적인 관측이 가능하여 재난 피해분석, 재난 모니터링 등 활용도가 증가하고 있다. 하지만 광학위성영상 특성상 구름으로 인한 결측된 영역으로 인해 주기적인 재난 모니터링에는 한계가 있어 결측된 영역의 복원 연구가 필요하다. 본 연구에서는 Landsat 8호 영상 취득 시 제공되는 QA밴드를 이용하여 구름 및 구름그림자를 탐지 및 제거하고, STARFM 알고리즘을 통해 제거된 영역의 영상 복원을 수행하였다. 복원된 영상은 기존의 영상 복원 방법으로 복원된 영상과 MLC 기법을 통해 정확도를 비교하였다. 그 결과, STARFM으로 인한 복원방법이 전체정확도 89.40%로, 기존의 영상 복원 방법보다 효율적인 복원방법임을 확인하였다. 따라서 본 연구결과를 통해 향후 Landsat 위성영상을 이용한 재난분석 수행 시 활용도를 높일 수 있을 것으로 기대된다.

• Nutrition Research and Practice
• /
• 제13권6호
• /
• pp.521-528
• /
• 2019

BACKGROUND/OBJECTIVES: The aim of this study was to develop Korean food image detection and recognition model for use in mobile devices for accurate estimation of dietary intake. MATERIALS/METHODS: We collected food images by taking pictures or by searching web images and built an image dataset for use in training a complex recognition model for Korean food. Augmentation techniques were performed in order to increase the dataset size. The dataset for training contained more than 92,000 images categorized into 23 groups of Korean food. All images were down-sampled to a fixed resolution of $150{\times}150$ and then randomly divided into training and testing groups at a ratio of 3:1, resulting in 69,000 training images and 23,000 test images. We used a Deep Convolutional Neural Network (DCNN) for the complex recognition model and compared the results with those of other networks: AlexNet, GoogLeNet, Very Deep Convolutional Neural Network, VGG and ResNet, for large-scale image recognition. RESULTS: Our complex food recognition model, K-foodNet, had higher test accuracy (91.3%) and faster recognition time (0.4 ms) than those of the other networks. CONCLUSION: The results showed that K-foodNet achieved better performance in detecting and recognizing Korean food compared to other state-of-the-art models.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2017년도 학술발표회
• /
• pp.191-191
• /
• 2017

Floods have become more widespread and frequent among natural disasters and consisted significant losses of lives and properties worldwide. Flood's impacts are threatening socio-economic and people's lives in the Mekong River Basin every year. The objective of this study is to identify the flood hazard areas and inundation depth in the Mekong River Basin. A rainfall-runoff and flood inundation model is necessary to enhance understanding of characteristic of flooding. Rainfall-Runoff-Inundation (RRI) model, a two-dimensional model capable of simulating rainfall-runoff and flood inundation simultaneously, was applied in this study. HydoSHEDS Topographical data, APPRODITE precipitation, MODIS land use, and river cross section were used as input data for the simulation. The Shuffled Complex Evolution (SCE-UA) global optimization method was integrated with RRI model to calibrate the sensitive parameters. In the present study, we selected flood event in 2000 which was considered as 50-year return period flood in term of discharge volume of 500 km3. The simulated results were compared with observed discharge at the stations along the mainstream and inundation map produced by Dartmouth Flood Observatory and Landsat 7. The results indicated good agreement between observed and simulated discharge with NSE = 0.86 at Stung Treng Station. The model predicted inundation extent with success rate SR = 67.50% and modified success rate MSR = 74.53%. In conclusion, the RRI model was successfully used to simulate rainfall runoff and inundation processes in the large scale Mekong River Basin with a good performance. It is recommended to improve the quality of the input data in order to increase the accuracy of the simulation result.

• Structural Monitoring and Maintenance
• /
• 제2권3호
• /
• pp.283-300
• /
• 2015

Visual condition inspections remain paramount to assessing the current deterioration status of a bridge and assigning remediation or maintenance tasks so as to ensure the ongoing serviceability of the structure. However, in recent years, there has been an increasing backlog of maintenance activities. Existing research reveals that this is attributable to the labour-intensive, subjective and disruptive nature of the current bridge inspection method. Current processes ultimately require lane closures, traffic guidance schemes and inspection equipment. This not only increases the whole-of-life costs of the bridge, but also increases the risk to the travelling public as issues affecting the structural integrity may go unaddressed. As a tool for bridge condition inspections, Unmanned Aerial Vehicles (UAVs) or, drones, offer considerable potential, allowing a bridge to be visually assessed without the need for inspectors to walk across the deck or utilise under-bridge inspection units. With current inspection processes placing additional strain on the existing bridge maintenance resources, the technology has the potential to significantly reduce the overall inspection costs and disruption caused to the travelling public. In addition to this, the use of automated aerial image capture enables engineers to better understand a situation through the 3D spatial context offered by UAV systems. However, the use of UAV for bridge inspection involves a number of critical issues to be resolved, including stability and accuracy of control, and safety to people. SLAM (Simultaneous Localisation and Mapping) is a technique that could be used by a UAV to build a map of the bridge underneath, while simultaneously determining its location on the constructed map. While there are considerable economic and risk-related benefits created through introducing entirely new ways of inspecting bridges and visualising information, there also remain hindrances to the wider deployment of UAVs. This study is to provide a context for use of UAVs for conducting visual bridge inspections, in addition to addressing the obstacles that are required to be overcome in order for the technology to be integrated into current practice.

• 한국컴퓨터정보학회논문지
• /
• 제25권6호
• /
• pp.81-89
• /
• 2020

우리가 SNS상에서 흔하게 접하는 온라인 리뷰에는, 소비자들의 선호도에 영향을 미치는 다양한 평가정보가 복합적으로 포함되어 있지만 이를 매우 간단한 형태의 수치(또는 평점)로 제공하는 것이 일반적이다. 이러한 리뷰에서, 소비자가 원하는 구체적인 정보를 얻고, 이를 구매를 위한 판단에 활용하기란 쉽지 않다. 따라서 본 연구에서는 한국어로 작성된 음식점 리뷰를 대상으로, 감성분석을 수행하여 평가항목별로 세분화된 평점을 제공 가능한 예측 방법론을 제안한다. 이를 위해, 음식점의 주요 평가항목으로 '음식', '가격', '서비스', '분위기'를 선정하고, 평가항목별 맞춤형 감성사전을 새롭게 구축한다. 또한 평가항목별 리뷰 문장을 분류하고 감성분석을 통해 세분화된 평점을 예측하여 소비자가 의사결정에 활용 가능한 추가적인 정보를 제공한다. 마지막으로, MAE와 RMSE를 평가지표로 사용하여 기존의 연구보다 제안기법의 평점 예측 정확도가 향상되었음을 보이며, 제안 방법론의 활용 사례도 제시한다.

• Nuclear Engineering and Technology
• /
• 제22권1호
• /
• pp.12-19
• /
• 1990

1981년 6월 9일 고리 1호기 원자력발전소에서 발생한 외부 전원 상실사고 자료를 근거로 RELAP5/MOD2코드모델 평가를 하였다. 계산된 주요 열ㆍ수력학 변수를 실측자료와 비교 분석하였으며 증기발생기의 Nodalization 민감도 분석이 수행되었다. 계산된 열ㆍ수력학 변수는 실측치와 비교적 잘 일치하고 있으며, 이러한 유형의 사고 분석에 RELAP5/MOD2가 적합하다는 것을 보였다. 그러나 가압기 압력과 수위변동에서는 상당한 차이를 보였으며 높게 계산되었다. 이러한 사실은 RELAP5의 수직관에서의 층류 열전달 모델에 기인하는 것으로 해당모델의 개선을 요하고 있다는 것을 알았다. 그리고 증기발생기의 Nodalization 연구를 통하여 수위변동을 잘 예측하기 1위해서는 증기발생기 증기 Dome와 Downcomer사이에 압력을 전달시켜주는 유로를 모델링 하여야 한다는 것을 알았다.

• 한국토양비료학회지
• /
• 제44권3호
• /
• pp.517-526
• /
• 2011

Soil structure plays an important role in ecological system, since it controls transport and storage of air, gas, nutrients and solutions. The study of soil structure requires an understanding of the interrelations and interactions between the diverse soil components at various levels of organization. Investigations of the spatial distribution of pore/particle arrangements and the geometry of soil pore space can provide important information regarding ecological or crop system. Because of conveniences in image analyses and accuracy, these investigations have been thrived for a long time. Image analyses from soil sections through impregnated blocks of undisturbed soil (2 dimensional image analyses) or from 3 dimensional scanned soils by computer tomography allow quantitative assessment of the pore space. Image analysis techniques can be used to classify pore types and quantify pore structure without inaccurate or hard labor in laboratory. In this paper, the last 50 years of the soil image analyses have been presented and measurements on various soil scales were introduced, as well. In addition to history of image analyses, a couple of examples for soil image analyses were displayed. The discussion was made on the applications of image analyses and techniques to quantify pore/soil structure.

• Imaging Science in Dentistry
• /
• 제51권3호
• /
• pp.237-242
• /
• 2021

Purpose: The aim of this study was to analyse and review deep learning convolutional neural networks for detecting and diagnosing early-stage dental caries on periapical radiographs. Materials and Methods: In order to conduct this review, the Preferred Reporting Items for Systematic Reviews and Meta-Analyses(PRISMA) guidelines were followed. Studies published from 2015 to 2021 under the keywords(deep convolutional neural network) AND (caries), (deep learning caries) AND (convolutional neural network) AND (caries) were systematically reviewed. Results: When dental caries is improperly diagnosed, the lesion may eventually invade the enamel, dentin, and pulp tissue, leading to loss of tooth function. Rapid and precise detection and diagnosis are vital for implementing appropriate prevention and treatment of dental caries. Radiography and intraoral images are considered to play a vital role in detecting dental caries; nevertheless, studies have shown that 20% of suspicious areas are mistakenly diagnosed as dental caries using this technique; hence, diagnosis via radiography alone without an objective assessment is inaccurate. Identifying caries with a deep convolutional neural network-based detector enables the operator to distinguish changes in the location and morphological features of dental caries lesions. Deep learning algorithms have broader and more profound layers and are continually being developed, remarkably enhancing their precision in detecting and segmenting objects. Conclusion: Clinical applications of deep learning convolutional neural networks in the dental field have shown significant accuracy in detecting and diagnosing dental caries, and these models hold promise in supporting dental practitioners to improve patient outcomes.