• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.885-887
• /
• 2003

The purpose of this investigation is to generate true orthophotos from high resolution satellite images. The major works of this research include 4 parts: (1) determination of orientation parameters, (2) generating traditional orthophotos using terrain model, (3) relief correction for buildings, and (4) process for hidden areas. To determine the position of satellites, we correct the onboard orientation parameters to fine tune the orbit. In the generation of traditional orthophotos, we employ orientation parameters and digital terrain model(DTM) to rectify tilt displacements and relief displacements for terrain. We, then, compute relief displacements for buildings with digital building model (DBM). To avoid double mapping, we detect hidden areas. Due to the satellite’s small field of view, an efficient method for the detection of hidden areas and building rectification will be proposed in this paper. Test areas cover the city of Kaohsiung in southern Taiwan. Test images are from the QuickBird satellite.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.390-393
• /
• 2007

KOMPSAT-2, the first Korean high resolution earth observing satellite, continuously acquires high resolution images since July 2006. The quality of satellite images should be geometrically and radiometrically ensured before distribution to users. This study focused on absolute radiometric calibration which is a prerequisite procedure to ensure the radiometric quality of optical satellite images. In this study, we performed reflectance-based vicarious calibration methods on several uniform targets collected through several field campaigns in 2007. The radiative transfer model, MODTRAN, was used to estimate the amount of energy received at the sensor. The energy reached at the sensor are affected by several factors such as reflectance of targets, atmospheric condition, geometry condition between Sun and the sensor, etc. This study proposes the absolute radiometric calibration coefficients of KOMPSAT-2 MSC images combining several types of collected data through field works and tried to compare dynamic range of sensor-detected energy with other commercial high resolution sensors.

• 디지털콘텐츠학회 논문지
• /
• 제19권6호
• /
• pp.1197-1205
• /
• 2018

본 논문에서는 함정전투체계의 EOTS나 IRST에서 획득한 영상을 초고해상도 영상으로 복원한다. 저해상도에서 초고해상도의 영상을 생성하는 생성 모델과 이를 판별하는 판별 모델로 구성된 생성적 적대 신경망을 이용하고, 다양한 학습 파라미터의 변화를 통한 최적의 값을 제안한다. 실험에 사용되는 학습 파라미터는 crop size와 sub-pixel layer depth, 학습 이미지 종류로 구성되며, 평가는 일반적인 영상 품질 평가 지표에 추가적으로 특징점 추출 알고리즘을 함께 사용하였다. 그 결과, Crop size가 클수록, Sub-pixel layer depth가 깊을수록, 고해상도의 학습이미지를 사용할수록 더 좋은 품질의 영상을 생성한다.

• 한국신재생에너지학회:학술대회논문집
• /
• 한국신재생에너지학회 2009년도 춘계학술대회 논문집
• /
• pp.463-466
• /
• 2009

The numerical simulation optimized by Four Dimensional Data Assimilation (FDDA) with Quick Scatterometer (QuikSCAT) data is carried out to evaluate wind resource characteristics at various heights in the southeastern area of the Korean Peninsula, where wind farms are planned to be built on on- and off-shore as well as comparable diurnal wind variations are characterized at the surface. The temporal and spatial distributions of modeled wind speeds showed good agreement with the observations based on the temporal variation analysis. Model results indicate that the higher model is performed in resolution, the more precise results is at turbine hub height. Occasionally, wind speed variations for each numerical resolution has a different regional and seasonal variations. In the coast area, hub height wind speed of 9km-resolution is simillar to that of 3km-resolution. On the other hand, hub height wind speed of 3km-resolution is simillar to that of 1km-resolution in the Jiri mountainous area.

• Ocean and Polar Research
• /
• 제35권2호
• /
• pp.135-146
• /
• 2013

This study investigates the characteristic of the Tsushima Warm Current from an assimilated high resolution global ocean prediction model, $1/12^{\circ}$ Global HYbrid Coordiate Ocean Model (HYCOM). The model results were verified through a comparison with current measurements obtained by acoustic Doppler current profiler (ADCP) mounted on the passenger ferryboat between Busan, Korea, and Hakata, Japan. The annual mean transport of the Tsushima Warm Current was 2.56 Sverdrup (Sv) (1 Sv = $10^6m^3s^{-1}$), which is similar to those from previous studies (Takikawa et al. 1999; Teague et al. 2002). The volume transport time series of the Tsushima Warm Current from HYCOM correlates to a high degree with that from the ADCP observation (the correlation coefficient between the two is 0.82). The spatiotemporal structures of the currents as well as temperature and salinity from HYCOM are comparable to the observed ones.

• 한국정보전자통신기술학회논문지
• /
• 제16권1호
• /
• pp.41-49
• /
• 2023

CNN(Convolutional Neural Network) 알고리즘은 인공신경망 구현에 활용되는 대표적인 알고리즘으로 기존 FNN(Fully connected multi layered Neural Network)의 문제점인 연산의 급격한 증가와 낮은 객체 인식률을 개선하였다. 그러나 IT 기기들의 급격한 발달로 최근 출시된 스마트폰 및 태블릿의 카메라에 촬영되는 이미지들의 최대 해상도는 108MP로 약 1억 8백만 화소이다. 특히 CNN 알고리즘은 고해상도의 단순 이미지를 학습 및 처리에 많은 비용과 시간이 요구된다. 이에 본 논문에서는 고해상도 단순 이미지의 객체 분류 학습모델 구현을 위한 개선된 CNN 알고리즘을 제안한다. 제안하는 알고리즘은 고해상도의 이미지들의 학습모델 생성 시간을 감소하기 위해 CNN 알고리즘의 풀링계층의 Max Pooling 알고리즘 연산을 위한 인접 행렬 값을 변경한다. 변경한 행렬 값마다 4MP, 8MP, 12MP의 고해상도 이미지들의 처리할 수 있는 학습 모델들을 구현한다. 성능평가 결과, 제안하는 알고리즘의 학습 모델의 생성 시간은 12MP 기준 약 36.26%의 감소하고, 학습 모델의 객체 분류 정확도와 손실률은 기존 모델 대비 약 1% 이내로 오차 범위 안에 포함되어 크게 문제가 되지 않는다. 향후 본 연구에서 사용된 학습 데이터보다 다양한 이미지 종류 및 실제 사진으로 학습 모델을 구현한 실질적인 검증이 필요하다.

• 대한원격탐사학회지
• /
• 제27권3호
• /
• pp.303-314
• /
• 2011

Surface albedo is an important parameter of the surface energy budget, and its accurate quantification is of major interest to the global climate modeling community. Therefore, in this paper, we consider the direct solution of kernel based bidirectional reflectance distribution function (BRDF) models for retrieval of normalized reflectance of high resolution satellite. The BRD effects can be seen in satellite data having a wide swath such as SPOT/VGT (VEGETATION) have sufficient angular sampling, but high resolution satellites are impossible to obtain sufficient angular sampling over a pixel during short period because of their narrow swath scanning when applying semi-empirical model. This gives a difficulty to run BRDF model inferring the reflectance normalization of high resolution satellites. The principal purpose of the study is to estimate normalized reflectance of high resolution satellite (RapidEye) through BRDF components from SPOT/VGT. We use semi-empirical BRDF model to estimated BRDF components from SPOT/VGT and reflectance normalization of RapidEye. This study used SPOT/VGT satellite data acquired in the S1 (daily) data, and within this study is the multispectral sensor RapidEye. Isotropic value such as the normalized reflectance was closely related to the BRDF parameters and the kernels. Also, we show scatter plot of the SPOT/VGT and RapidEye isotropic value relationship. The linear relationship between the two linear regression analysis is performed by using the parameters of SPOTNGT like as isotropic value, geometric value and volumetric scattering value, and the kernel values of RapidEye like as geometric and volumetric scattering kernel Because BRDF parameters are difficult to directly calculate from high resolution satellites, we use to BRDF parameter of SPOT/VGT. Also, we make a decision of weighting for geometric value, volumetric scattering value and error through regression models. As a result, the weighting through linear regression analysis produced good agreement. For all sites, the SPOT/VGT isotropic and RapidEye isotropic values had the high correlation (RMSE, bias), and generally are very consistent.

• 대기
• /
• 제22권3호
• /
• pp.357-365
• /
• 2012

High spatio-temporal resolution hydrologic components can give important information to monitor natural disaster. The objective of this study is to create high spatial-temporal resolution gridded hydrologic components using TOPLATS distributed land surface model and evaluate their accuracy. For this, Andong dam basin is selected as study area and TOPLATS model is constructed to create hourly simulated values in every $1{\times}1km^2$ cell size. The observed inflow at Andong dam and soil moisture at Andong AWS site are collected to directly evaluate the simulated one. RMSEs of monthly simulated flow for calibration (2003~2006) and verification (2007~2009) periods show 36.87 mm and 32.41 mm, respectively. The hourly simulated soil moisture in the cell located Andong observation site for 2009 is well fitted with observed one at -50 cm. From this results, the cell based hydrologic components using TOPLATS distributed land surface model show to reasonably represent the real hydrologic condition in the field. Therefore the model driven hydrologic information can be used to analyze local water balance and monitor natural disaster caused by the severe weather.

• 대기
• /
• 제18권1호
• /
• pp.55-70
• /
• 2008

The global time slice approach is a transient experiment using high resolution atmosphere-only model with boundary condition from the low resolution globally coupled ocean-atmosphere model. The present study employs this "time slice concept" using ECHAM4 atmosphere-only model at a horizontal resolution of T106 with the lower boundary forcing obtained from a lower-resolution (T42) greenhouse gas + aerosol forcing experiment performed using the ECHO-G/S (ECHAM4/HOPE-G) coupled model. In order to assess the impact of horizontal resolution on simulated East Asian summer monsoon climate, the differences in climate response between the time slice experiments of the present and that of IPCC SRES AR4 participating 21 models including coarser (T30) coupled model are compared. The higher resolution model from time slice experiment in the present climate show successful performance in simulating the northward migration and the location of the maximum rainfall during the rainy season over East Asia, although its rainfall amount was somewhat weak compared to the observation. Based on the present climate simulation, the possible change of East Asian summer monsoon rainfall in the future climate by the IPCC SRES A1B scenario, tends to be increased especially over the eastern part of Japan during July and September. The increase of the precipitation over this region seems to be related with the weakening of northwestern part of North Pacific High and the formation of anticyclonic flow over the south of Yangtze River in the future climate.

• 스마트미디어저널
• /
• 제9권4호
• /
• pp.17-25
• /
• 2020

In the image object classification problem, low-resolution images may have a negative impact on the classification result, especially when the classification method, such as a convolutional neural network (CNN) model, is trained on a high-resolution (HR) image dataset. In this paper, we analyze the behavior of applying a classical super-resolution (SR) method such as bicubic interpolation, and a deep CNN model such as SRCNN to enhance low-resolution (LR) weeds images used for classification. Using an HR dataset, we first train a CNN model for weeds image classification with a default input size of 128 × 128. Then, given an LR weeds image, we rescale to default input size by applying the bicubic interpolation or the SRCNN model. We analyze these two approaches on the Chonnam National University (CNU) weeds dataset and find that SRCNN is suitable for the image size is smaller than 80 × 80, while bicubic interpolation is convenient for a larger image.