• 대한원격탐사학회지
• /
• 제37권5_1호
• /
• pp.871-884
• /
• 2021

본 연구의 목적은 항공 및 위성영상을 활용한 토지피복 관련 인공지능 학습 데이터를 구축, 검증 및 알고리즘 적용의 효율화 방안을 연구하였다. 이를 위하여 토지피복 8개 항목에 대하여 고해상도의 항공영상 및 Sentinel-2 인공위성에서 얻은 이미지를 사용하여 0.51 m 및 10 m Multi-resolution 데이터셋을 구축하였다. 또한, 학습 데이터의 구성은 Fine data (총 17,000개) 와 Coarse data (총 33,000개)를 동시 구축 및 정밀한 변화 탐지 및 대규모 학습 데이터셋 구축이라는 2가지 목적을 달성하였다. 학습 데이터의 정확도를 위한 검수는 정제 데이터, 어노테이션 및 샘플링으로 3단계로 진행하였다. 최종적으로 검수가 완료된 학습데이터를 Semantic Segmentation 알고리즘 중 U-Net, DeeplabV3+에 적용하여, 결과를 분석하였다. 분석결과 항공영상 기반의 토지피복 평균 정확도는 U- Net 77.8%, Deeplab V3+ 76.3% 및 위성영상 기반의 토지피복에 대한 평균 정확도는 U-Net 91.4%, Deeplab V3+ 85.8%이다. 본 연구를 통하여 구축된 고해상도 항공영상 및 위성영상을 이용한 토지피복 인공지능 학습 데이터셋은 토지피복 변화 및 분류에 도움이 되는 참조자료로 활용이 가능하다. 향후 우리나라 전체를 대상으로 인공지능 학습 데이터셋 구축 시, 토지피복을 연구하는 다양한 인공지능 분야에 활용될 것으로 기대된다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1221-1223
• /
• 2003

With speediness of economy, the structure of land use has taken lots of change. How can we quickly and exactly obtain detailed land use/cover change information, and then we know land resource amount, quality, distributing and change direction. More and more high resolution satellite systems are under development. So we can make good use of RS data, existed GIS data and GPS data to extract change information and update map. In this paper a fully automated approach for detecting land use/cover change using remote sensing data with object-oriented classification based on GIS data, GPS data is presented (referring to Fig.1). At same time, I realize integrating raster with vector methods of updating the basic land use/land cover map based on 3S technology and this is becoming one of the most important developing direction in 3S application fields; land-use and cover change fields over the world. It has been successful applied in two tasks of The Ministry of Land and Resources P.R.C and taken some of benefit.

• 한국대기환경학회지
• /
• 제15권6호
• /
• pp.747-755
• /
• 1999

Effects of precipitation and cloud cover on high ozone days are examined by investigating the precipitation and average cloud cover before the ozone peak time within a day. High ozone days above 100 ppb in the Greater Seoul Area(GSA) for the ozone season from May to September are chosen for the analyses in terms of the surface meteorological data during 1990~1997. The result shows that the effect of precipitation on the rise of ozone concentration is definitely negative so that ozone concentration could not rise above 100ppb immediately after precipitation. But, the effect of cloud cover is associated with the variations of other meteorological parameters. The number of high ozone days with "zero" cloud cover is rather less than that with cloud cover of 1 to 4 since temperature is usually lower in "zero" cloud cover days. Furthermore, ozone concentration can rise above 100ppb even with full cloud cover when the wind is weak and the temperature is high.temperature is high.

• 한국CDE학회논문집
• /
• 제10권5호
• /
• pp.375-379
• /
• 2005

Durability of rubber dust cover in the ball joint for automotive suspension parts is analyzed by FEM and compared with experimental data. Upper open area of ball joint is sealed by dust cover for preventing outflow of the lubricating oil and intrusion of send, dust, water, etc. This rubber cover undergoes repeated loadings such as tension and compression while the car is running. Analysis about rubber material needs to consider every kinds of nonlinearities arise in finite element analysis, which are geometric nonlinearity due to large displacement and small strain, materially nonlinearity and nonlinear boundary condition such as contact. The deformation behavior of dust cover is analysed by using the commercial finite element program MARC. In the study, this program could solve these kinds of nonlinear analysis accurately. Finite element model of dust cover is considered as 3-dimensional half model based on 2-dimensional axisymmetric model. Material property of rubber is modeled by Ogden model and input data for calculation takes form uniaxial tension test of rubber specimen. The final object of the study is obtaining the design specification of dust covers and the result of analysis should be a useful data to design of rubber cover.

• 대기
• /
• 제21권4호
• /
• pp.373-389
• /
• 2011

This research focuses on the sensitivity of the WRF(Weather Research and Forecasting) Model according to three different land cover data(USGS(United States Geological Survey), MODIS(Moderate Resolution Imaging Spectroradiometer)30s+USGS, and KLC (Korea Land Cover)) for an event of sea breeze, occurred over the Gangwon Yeongdong region on 13 May 2009. Based on the observation, the easterly into Gangneung, due to the sea-breeze circulation, was identified between 1000 LST and 1640 LST. It did not reach beyond the Taebaek Mountain Range and thus the easterly was not observed near Daegwallyeong. On the other hand, the numerical simulations utilizing land cover data of USGS, MODIS30s+USGS, and KLC showed easterlies beyond the Taebaek Mountain Range up to Daegwallyeong. In addition, rather different penetration distances of each easterly, and different timings of beginning and ending of sea breeze were identified among the simulations. The Bias, MAE(Mean Absolute Error) and RMSE(Root Mean Square Error) of the wind from WRF simulation using MODIS30s+USGS land cover data were the least among the simulations particularly over Gangwon Yeongdong coastal area(Sokcho, Gangneung and Donghae), while those of the wind over the Gangwon Mountain area(Daegwallyeong and Jinbu) from the simulation using KLC land cover data were the least among them. The wind field over Gangwon Yeongdong coastal area from the simulation using USGS land cover data was rather poor among them.

• 대한원격탐사학회지
• /
• 제39권5_1호
• /
• pp.507-519
• /
• 2023

Multi-temporal optical images have been utilized for time-series monitoring of croplands. However, the presence of clouds imposes limitations on image availability, often requiring a cloud removal procedure. This study assesses the applicability of various machine learning algorithms for effective cloud removal in optical imagery. We conducted comparative experiments by focusing on two key variables that significantly influence the predictive performance of machine learning algorithms: (1) land-cover types of training data and (2) temporal variability of land-cover types. Three machine learning algorithms, including Gaussian process regression (GPR), support vector machine (SVM), and random forest (RF), were employed for the experiments using simulated cloudy images in paddy fields of Gunsan. GPR and SVM exhibited superior prediction accuracy when the training data had the same land-cover types as the cloud region, and GPR showed the best stability with respect to sampling fluctuations. In addition, RF was the least affected by the land-cover types and temporal variations of training data. These results indicate that GPR is recommended when the land-cover type and spectral characteristics of the training data are the same as those of the cloud region. On the other hand, RF should be applied when it is difficult to obtain training data with the same land-cover types as the cloud region. Therefore, the land-cover types in cloud areas should be taken into account for extracting informative training data along with selecting the optimal machine learning algorithm.

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 2005년도 학술발표논문집
• /
• pp.254-259
• /
• 2005

The shape of a streamflow hydrograph is very much controlled by the area and depth of snow cover in mountain area. The purpose of this study is to suggest extraction methods for snow cover area and depth using NOAA/AVHRR images in Soyanggang watershed. Snow cover area maps ware derived form channel 1, 3, 4 images of NOAA/AVHRR based on threshold value. In order to extract snow cover depth, snow cover area maps were overlaid daily snow depth data form 7 meteorological observation stations. Snow cover area and depth was mapped for period of Dec. 2002 and Mar. 2003. For evaluating snowmelt changes, depletion curve was created using daily snow cover area in the same period. It is necessary to compare these results with observed data and check the applicability of the suggested method in snowmelt simulation.

• 한국측량학회지
• /
• 제30권6_2호
• /
• pp.653-663
• /
• 2012

Using soft classification, it is possible to obtain the land cover proportions from the remotely sensed image. These land cover proportions are then used as input data for a procedure called "super-resolution mapping" to produce the predicted hard land cover layers at higher resolution than the original remotely sensed image. Superresolution mapping can be implemented using a number of algorithms in which the Hopfield Neural Network (HNN) has showed some advantages. The HNN has improved the land cover classification through superresolution mapping greatly with the high resolution data. However, the super-resolution mapping is based on the spatial dependence assumption, therefore it is predicted that the accuracy of resulted land cover classes depends on the relative size of spatial features and the spatial resolution of the remotely sensed image. This research is to evaluate the capability of HNN to implement the super-resolution mapping for SPOT image to create higher resolution land cover classes with different zoom factor.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.13-18
• /
• 1999

Land cover map of 30 arc-second grid by NOAA AVHRR data for the whole Asia was produced by the authors as the project of the Asian Association on Remote Sensing(AARS). Land cover change monitoring of continental scale by satellite data needs preprocessing to remove undesirable factors due to noises, atmosphere, or the effect by solar zenith angle. The paper describes the method to remove these factors. The most important thing for better mapping/monitoring in the future is the accumulation of ground truth data by many land cover related researchers. The project of the development of Global Land Cover Ground Truth Database(GLCGT-DB) is proposed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1858-1872
• /
• 2023

With the advance of radar technologies, the availability of synthetic aperture radar (SAR) images increases. To improve application of SAR images, a management system for SAR images is proposed in this paper. The system provides trainable land cover classification module and display of SAR images on the map. Users of the system can create their own classifier with their data, and obtain the classified results of newly captured SAR images by applying the classifier to the images. The classifier is based on convolutional neural network structure. Since there are differences among SAR images depending on capturing method and devices, a fixed classifier cannot cover all types of SAR land cover classification problems. Thus, it is adopted to create each user's classifier. In our experiments, it is shown that the module works well with two different SAR datasets. With this system, SAR data and land cover classification results are managed and easily displayed.