• Korean Journal of Remote Sensing
• /
• v.34 no.6_2
• /
• pp.1239-1249
• /
• 2018

Optical remote sensing sensors provide visually more familiar images than radar images. However, it is difficult to discriminate sea ice types in optical images using spectral information based machine learning algorithms. This study addresses two topics. First, we propose a semantic segmentation which is a part of the state-of-the-art deep learning algorithms to identify ice types by learning hierarchical and spatial features of sea ice. Second, we propose a new approach by combining of semi-supervised and active learning to obtain accurate and meaningful labels from unlabeled or unseen images to improve the performance of supervised classification for multiple images. Therefore, we successfully added new labels from unlabeled data to automatically update the semantic segmentation model. This should be noted that an operational system to generate ice type products from optical remote sensing data may be possible in the near future.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.24 no.12
• /
• pp.1128-1139
• /
• 2013

KOMPSAT-5(KOrea Multi-Purpose SATellite-5) has a benefit of continuously conducting its mission in all weather and even night by loading SAR(Synthetic Aperture Radar) payload, which is different from optical sensor of KOMPSAT-2 satellite. During IOT(In-Orbit Test) periods, SAR image calibration should be conducted through ground target of which location and RCS is pre-determined. Differently from the conventional corner reflector, active transponder has a capability to change its internal transfer gain and delay, which allows active transponder to be shown in a pixel of SAR image with very high radiance and virtual location. In this paper, the development of active transponder is presented from design to I&T(Integration and Test).

• Journal of Korean Society for Geospatial Information Science
• /
• v.17 no.1
• /
• pp.131-139
• /
• 2009

The existing vessel monitoring system using the ground surveillance radar has a difficulty in monitoring ships continuously due to the limited range of detecting ships. For resolving this problem, we carry out a research on ship detection which is to be the core technology of vessel monitoring system for ocean monitoring using SAR imagery. There are two different methods of detecting ships in SAR imagery: detection of the ship target itself and detection of the ship wake. In this paper, we mainly focus on algorithms which detect the ship itself, and also present the accuracy test after extracting positional and directional figures of the ships. After rectifying input SAR imagery using polynomial transformation, we use Wiener filter to remove speckle noises. A labeling technique and morphological filtering in conjunction with Otsu's method are used to automatically detect the ships based on the image processing domain. For ground truth data, information from a radar system is used, which allows assessing the accuracy of the proposed method. The results show that the proposed method has the high potential in automatically detecting the ships and its positional/directional figures in a fast way.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_3
• /
• pp.1415-1425
• /
• 2018

Kompsat-5 is the first Earth Observation Satellite which is equipped with an SAR in Korea. SAR images are generated by receiving signals reflected from an object by microwaves emitted from a SAR antenna. Because the wavelengths of microwaves are longer than the size of particles in the atmosphere, it can penetrate clouds and fog, and high-resolution images can be obtained without distinction between day and night. However, there is no color information in SAR images. To overcome these limitations of SAR images, colorization of SAR images using Cycle GAN, a deep learning model developed for domain translation, was conducted. Training of Cycle GAN is unstable due to the unsupervised learning based on unpaired dataset. Therefore, we proposed MS Cycle GAN applying multi-scale discriminator to solve the training instability of Cycle GAN and to improve the performance of colorization in this paper. To compare colorization performance of MS Cycle GAN and Cycle GAN, generated images by both models were compared qualitatively and quantitatively. Training Cycle GAN with multi-scale discriminator shows the losses of generators and discriminators are significantly reduced compared to the conventional Cycle GAN, and we identified that generated images by MS Cycle GAN are well-matched with the characteristics of regions such as leaves, rivers, and land.

• Economic and Environmental Geology
• /
• v.38 no.4 s.173
• /
• pp.381-394
• /
• 2005

Mokpo city is a coastal city located at the south western coast of the Korean Peninsula. Large regions within Mokpo are subjected to significant subsidence because about $70\%$ of the city area is a reclaimed land from the sea. Although no confidential quantitative measurements are available up to the present, the subsidence rate is as much as several cm per year. In this study, we aimed to estimate the subsidence rate over Mokpo city by using twenty-six JERS-1 SAR dataset from September 1992 to October 1998. Several tens of differential interferograms were processed from JERS-1 dataset and STRM 3-arc DEM. The results indicate continuous subsidence in Dongmyung-dong, Hadang-dong and Wonsan-dong in city, and the subsidence velocity reach over 4 cm/yr in the most highly sinking area. For facilitating the analysis of time-varying surface change, we also carried out an interferometric SAR time series analysis using permanent scatterer and consequently determined space-time maps of surface deformation at each acquisition time of JERS- 1 SAR.

• Korean Journal of Remote Sensing
• /
• v.30 no.1
• /
• pp.83-107
• /
• 2014

This study presents spatial characteristics of cloud using satellite image in the extreme heavy snowfall of the Yeongdong region. 3 extreme heavy snowfall events in the Yeongdong region during the recent 12 years (2001 ~ 2012) are selected for which the fresh snow cover exceed 50 cm/day. Spatial characteristics (minimum brightness temperature; Tmin, cloud size, center of cloud-cell) of cloud are analyzed by tracking main cloud-cell related with these events. These characteristics are compared with radar precipitation in the Yeongdong region to investigate relationship between cloud and precipitation. The results are summarized as follows, selected extreme heavy snowfall events are associated with the isolated, well-developed, and small-scale convective cloud which is developing over the Yeongdong region or moving from over East Korea Bay to the Yeongdong region. During the period of main precipitation, cloud-cell Tmin is low ($-40{\sim}-50^{\circ}C$) and cloud area is small (17,000 ~ 40,000 $km^2$). Precipitation area (${\geq}$ 0.5 mm/hr) from radar also shows small and isolated shape (4,000 ~ 8,000 $km^2$). The locations of the cloud and precipitation are similar, but in there centers are located closely to the coast of the Yeongdong region. In all events the extreme heavy snowfall occur in the period a developed cloud-cell was moving into the coastal waters of the Yeongdong. However, it was found that developing stage of cloud and precipitation are not well matched each other in one of 3 events. Water vapor image shows that cloud-cell is developed on the northern edge of the dry(dark) region. Therefore, at the result analyzed from cloud and precipitation, selected extreme heavy snowfall events are associated with small-scale secondary cyclone or vortex, not explosive polar low. Detection and tracking small-scale cloud-cell in the real-time forecasting of the Yeongdong extreme heavy snowfall is important.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.239-239
• /
• 2018

위성 및 드론을 이용한 원격탐사 기술이 발전하고 다양한 산출물이 나타남에 따라 수자원 및 하천관리 분야에서 원격탐사기술 활용의 폭이 넓어지고 있다. 원격탐사 영상에서 획득할 수 있는 기본적인 가시영상 이외에도 적외영상, 초분광영상, 수위정보, 레이더 반사도 등을 활용하여 하천정보를 추정하려는 시도가 이루어져왔다. 본 연구에서는 원격탐사 영상에서 획득한 하폭을 기반으로 수리학적 하천유량산정을 기법을 적용하기 위해 등류 및 부등류 해석이 가능한 알고리즘과 프로그램을 개발하였다. 등류해석을 위해 GUI 기반 프로그램을 개발하였으며, 특정 하폭에서의 하천유량을 신속하게 계산할 수 있도록 단면 특성분석 모듈과 운동파 방정식 기반의 Manning 유속공식이 적용되도록 구성하였다. 또한, 부등류해석을 위해 스크립트기반의 프로그램을 개발하였다. 부등류 해석 프로그램에는 하천유량을 경계조건으로 수위를 계산하는 일반적인 부등류 수면곡선식의 해석절차를 하폭기반 원격하천 유량 산정 목적에 맞게 재구성하여 원격탐사기술로 획득한 하폭을 경계조건으로 하천 유량을 시산하는 알고리즘을 구현하였다. 본 프로그램을 활용하여 한국건설기술연구원 하천실험센터에서 드론을 이용한 등류/부등류 실험결과를 해석하였으며, 등류 흐름조건에서는 두 가지 해석방법 각각 14.3%, 14.7%의 유사한 평균상대오차를 나타내었고 부등류 흐름조건에서는 등류해석은 62.6%, 부등류해석은 15.8%의 평균상대오차를 나타내었다. 실규모하천에서의 원격하천유량 산정을 위해서는 등류기반 해석방법에 비해 비균일 하천단면에서의 부등류 현상을 모의할 수 있는 하폭기반 부등류 수면곡선의 시산 알고리즘이 유리한 것으로 판단된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.230-230
• /
• 2023

딥러닝 알고리즘 중 과거의 정보를 저장하는 문제(장기종속성 문제)가 있는 단순 RNN(Simple Recurrent Neural Network)의 단점을 해결한 LSTM(Long short-term memory)이 등장하면서 특정한 유역의 강우-유출 모형을 구축하는 연구가 증가하고 있다. 그러나 하나의 모형으로 모든 유역에 대한 유출을 예측하는 지역화 강우-유출 모형은 서로 다른 유역의 식생, 지형 등의 차이에서 발생하는 수문학적 행동의 차이를 학습해야 하므로 모형 구축에 어려움이 있다. 따라서, 본 연구에서는 국내 12개의 유역에 대하여 LSTM 기반 분포형 지역화 강우-유출 모형을 구축한 이후 강우 이외의 보조 자료에 따른 정확도를 살펴보았다. 국내 12개 유역의 7년 (2012.01.01-2018.12.31) 동안의 49개 격자(4km²)에 대한 10분 간격 레이더 강우, MODIS 위성 이미지 영상을 활용한 식생지수 (Normalized Difference Vegetation Index), 10분 간격 기온, 유역 평균 경사, 단순 하천 경사를 입력자료로 활용하였으며 10분 간격 유량 자료를 출력 자료로 사용하여 LSTM 기반 분포형 지역화 강우-유출 모형을 구축하였다. 이후 구축된 모형의 성능을 검증하기 위해 학습에 사용되지 않은 3개의 유역에 대한 자료를 활용하여 Nash-Sutcliffe Model Efficiency Coefficient (NSE)를 확인하였다. 식생지수를 보조 자료를 활용하였을 경우 제안한 모형은 3개의 검증 유역에 대하여 하천 흐름을 높은 정확도로 예측하였으며 딥러닝 모형이 위성 자료를 통하여 식생에 의한 차단 및 토양 침투와 같은 동적 요소의 학습이 가능함을 나타낸다.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1731-1745
• /
• 2023

Within the framework of the post-2020 climate regime, the Paris Agreement's emphasis on Nationally Determined Contributions and Biennial Transparency Reporting is paramount in addressing its long-term temperature goal. A salient issue is the treatment of wetland ecosystems within the context of Land Use, Land-Use Change, and Forestry, as defined by the Intergovernmental Panel on Climate Change. In the 2019 National Inventory Report, wetlands were recategorized as emission sources due to their designation as inundated areas. This study employs C-band radar imagery to discriminate between inundated and non-inundated regions of wetlands, enabling the quantification of their spatial dynamics. The research capitalizes on 24-period Sentinel-1 satellite data to cover both the inundation and desiccation phases while centering its attention on Ungok Wetland, a Ramsar-designated inland wetland conservation area in Korea. The inundated area is quantitatively assessed through the integration of multi-temporal Sentinel-1 Single-Look Complex (SLC) data, aerial orthophotography, and inland wetland spatial information. Furthermore, the study scrutinizes fluctuations in the maximum and minimum inundated areas, with substantial changes corroborated via drone aerial reconnaissance. The outcomes of this investigation hold the potential to make substantive contributions to the refinement of national greenhouse gas absorption and emission factors, thereby informing the development of comprehensive greenhouse gas inventories. These efforts align directly with the overarching objectives of the Paris Agreement.

• Journal of the Korean Geosynthetics Society
• /
• v.21 no.4
• /
• pp.55-67
• /
• 2022

In this paper, fundamentals and recent development of the interferometric synthetic aperture radar, known as InSAR, technique for measuring ground deformation through satellite image analysis are presented together with case histories illustrating its applicability to urban ground deformation monitoring. A study area in Korea was selected and processed based on the muti-temporal time series InSAR analysis, namely SBAS (Small Baseline Subset)-InSAR and PS (Persistent Scatterers)-InSAR using Sentinel-1A SAR images acquired from the year 2014 onward available from European Space Agency Copernicus Program. The ground settlement of the study area for the temporal window of 2014-2022 was evaluated from the viewpoint of the applicability of the InSAR technique for urban infrastructure settlement monitoring. The results indicated that the InSAR technique can reasonably monitor long-term settlement of the study area in millimetric scale, and that the time series InSAR technique can effectively measure ground settlement that occurs over a long period of time as the SAR satellite provides images of the Korean Peninsula at regular time intervals while orbiting the earth. It is expected that the InSAR technique based on higher resolution SAR images with small temporal baseline can be a viable alternative to the traditional ground borne monitoring method for ground deformation monitoring in the 4^th industrial era.