• Korean Journal of Remote Sensing
• /
• v.40 no.4
• /
• pp.351-361
• /
• 2024

Satellite imagery contains various elements such as clouds, cloud shadows, and terrain shadows. Accurately identifying and eliminating these factors that complicate satellite image analysis is essential for maintaining the reliability of remote sensing imagery. For this reason, satellites such as Landsat-8, Sentinel-2, and Compact Advanced Satellite 500-1 (CAS500-1) provide Usable Data Masks(UDMs)with images as part of their Analysis Ready Data (ARD) product. Precise detection of clouds and their shadows is crucial for the accurate construction of these UDMs. Existing cloud and their shadow detection methods are categorized into threshold-based methods and Artificial Intelligence (AI)-based methods. Recently, AI-based methods, particularly deep learning networks, have been preferred due to their advantage in handling large datasets. This study aims to analyze the applicability of constructing UDMs for high-resolution satellite images through deep learning-based cloud and their shadow detection using open-source datasets. To validate the performance of the deep learning network, we compared the detection results generated by the network with pre-existing UDMs from Landsat-8, Sentinel-2, and CAS500-1 satellite images. The results demonstrated that high accuracy in the detection outcomes produced by the deep learning network. Additionally, we applied the network to detect cloud and their shadow in KOMPSAT-3/3A images, which do not provide UDMs. The experiment confirmed that the deep learning network effectively detected cloud and their shadow in high-resolution satellite images. Through this, we could demonstrate the applicability that UDM data for high-resolution satellite imagery can be constructed using the deep learning network.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.3
• /
• pp.199-208
• /
• 2019

As the number of available satellites increases and technology advances, image information outputs are becoming increasingly diverse and a large amount of data is accumulating. In this study, we propose a change detection method for high-resolution satellite images that uses transfer learning and a deep learning network to overcome the limit caused by insufficient training data via the use of pre-trained information. The deep learning network used in this study comprises convolutional layers to extract the spatial and spectral information and convolutional long-short term memory layers to analyze the time series information. To use the learned information, the two initial convolutional layers of the change detection network are designed to use learned values from 40,000 patches of the ISPRS (International Society for Photogrammertry and Remote Sensing) dataset as initial values. In addition, 2D (2-Dimensional) and 3D (3-dimensional) kernels were used to find the optimized structure for the high-resolution satellite images. The experimental results for the KOMPSAT-3A (KOrean Multi-Purpose SATllite-3A) satellite images show that this change detection method can effectively extract changed/unchanged pixels but is less sensitive to changes due to shadow and relief displacements. In addition, the change detection accuracy of two sites was improved by using 3D kernels. This is because a 3D kernel can consider not only the spatial information but also the spectral information. This study indicates that we can effectively detect changes in high-resolution satellite images using the constructed image information and deep learning network. In future work, a pre-trained change detection network will be applied to newly obtained images to extend the scope of the application.

• Proceedings of KOSOMES biannual meeting
• /
• 2008.05a
• /
• pp.125-127
• /
• 2008

허베이스피리트호 원유유출 사고는 2007년 12월7일 아침 7시6분경 서해안 만리포 북서쪽 10km 해상에서 크레인을 적재한 1만1800t급 바지선이 정박 중인 흥콩 선적 유조선 허베이 스피리트호(14만6000t급)와 부딪치면서 발생했다. 이와 같은 기름 유출 사고의 경우, 유출 범위를 정확하게 이해하는 것이 중요하다. 여기서는 위 사고 기간에 얻어진 인공위성 자료를 이용하여 기름 유출을 탐지하기 위한 연구결과를 소개한다. 광학과 마이로파영상에 대해 유출 범위의 계산 및 해석 알고리듬에 대한 현재까지의 결과를 소개한다. 광학영상으로는 아리랑 2호 (다목적 실용위성 2호, KOMPSAT II) MSC(Multi Spectral Camera)자료가 사용되었으며, 합성개구레이더로는 ENVISAT ASAR, TerraSAR-X 및 ALOS PALSAR의 자료가 사용되었다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.1
• /
• pp.50-61
• /
• 2010

This study was carried out to find out the way to build a comprehensive wetland ecosystem database using the technique of remote sensing and Geographic Information System. A Landsat TM image (taken in Oct. 30, 2002), Kompsat-2 images (Jan. 17, 2008 & Nov. 20, 2008), LiDAR(Mar. 1, 2009) were used for the primary source for the image analysis. Field surveys were conducted March to August of 2009 to help image analysis and examine the results. An actual wetland vegetation map was created based on the field survey. Satellite images were analyzed by unsupervised and supervised classification methods and finally categorized into such classes as Phragmites australis community, mixed community, sand beach, Scirpus planiculmis community and non-vegetation intertidal area. The map of wetland productivity was developed based on the productivity of Phragmites australis and the relationship to the proximity of adjacent water bodies. The developed 3 dimensional wetland map showed such several potential applications as flood inundation, birds flyway viewsheds and benthos distribution. Considering these results, we concluded that it is possible to use the remote sensing and GIS techniques for producing wetland ecosystem spatial database and these techniques are very effective for the development of the national wetland inventory in Korea.

• Korean Journal of Remote Sensing
• /
• v.25 no.2
• /
• pp.145-154
• /
• 2009

High spatial resolution satellite image classification has a limitation when only using the spectral information due to the complex spatial arrangement of features and spectral heterogeneity within each class. Therefore, the extraction of the spatial information is one of the most important steps in high resolution satellite image classification. This study proposes a new spatial feature extraction method, named SSI(Shape-Size Index). SSI uses a simple region-growing based image segmentation and allocates spatial property value in each segment. The extracted feature is integrated with spectral bands to improve overall classification accuracy. The classification is achieved by applying a SVM(Support Vector Machines) classifier. In order to evaluate the proposed feature extraction method, KOMPSAT-2 and QuickBird-2 data are used for experiments. It is demonstrated that proposed SSI algorithm leads to a notable increase in classification accuracy.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.4
• /
• pp.13-20
• /
• 2013

Due to the global warming, international agreements have been propelled by industrialized countries. These days, there are various studies and projects to reduce the carbon emission quantity in South Korea, because South Korea is a strong candidate for a newly industrialized nation by Kyoto Protocol. Therefore, this study arranges plans to create various thematic map by producing database that can manage various datum based on grid spatial objects to manage quantity of forest biomass and carbon dioxide. Moreover, this study designs a system to create forest biomass by using the best method of calculation with LiDAR data and KOMPSAT-2 satellite images. In addition, this study designs a biomass monitoring system for public institutions to register biomass, suggesting actual plans to extract, manage, and utilized forest biomass.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.4
• /
• pp.259-266
• /
• 2015

Change detection using the heterogeneous data such as aerial images, aerial LiDAR (Light Detection And Ranging), and satellite images needs to be developed to efficiently monitor the complicating land use change. We approached this problem not relying on the intensity value of the geospatial image, but by using RECC(Relative Edge Cross Correlation) which is based on the edge information over the urban and suburban area. The experiment was carried out for the aerial LiDAR data with high-resolution Kompsat-2 and −3 images. We derived the optimal window size and threshold value for RECC-based change detection, and then we observed the overall change detection accuracy of 80% by comparing the results to the manually acquired reference data.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.1
• /
• pp.9-17
• /
• 2014

The Vegetation cover is a significant factor to comprehend characteristics of the ground surface for meterological and hydrological models, which measure energy in the atmosphere or predict the runoff of ground surface. Deardorff introduced vegetation cover fraction to quantitatively comprehend the vegetation cover in 1978. After Deardorff, most of previous researches were conducted on low-resolution or high-resolution images, but only few researches on Landsat that are in medium-resolution images. Therefore, this study aims to investigate a way of calculating the vegetation cover fraction by using NDVI of Landsat images, which were hardly handled previously. For accurate vegetation cover fraction, we compared the evaluated parameters from this study with past vegetation cover fraction parameters that have been calculated for using NDVI of Landsat OLI images. The result of research was shown that NDVI is quite correlated with the vegetation fraction cover in the previous researches. In fact, RMSE of vegetation cover fraction values that obtained through the suggested parameters on this study showed the highest accuracy of 7.3% among all the cases.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_4
• /
• pp.1173-1183
• /
• 2023

Over the past 20 years, Korea's overall import and export cargo volume has increased at an average annual rate of approximately 5.3%. About 99% of the cargo is still being transported by sea. Due to recent increases in maritime cargo volume, congestion in maritime logistics has become challenging due to factors such as the COVID-19 pandemic and conflicts. Continuous monitoring of ports has become crucial. Various ground observation systems and Automatic Identification System (AIS) data have been utilized for monitoring ports and conducting numerous preliminary studies for the efficient operation of container terminals and cargo volume prediction. However, small and developing countries' ports face difficulties in monitoring due to environmental issues and aging infrastructure compared to large ports. Recently, with the increasing utility of artificial satellites, preliminary studies have been conducted using satellite imagery for continuous maritime cargo data collection and establishing ocean monitoring systems in vast and hard-to-reach areas. This study aims to visually detect ships docked at berths in the Busan New Port using high-resolution satellite imagery and quantitatively evaluate berth utilization rates. By utilizing high-resolution satellite imagery from Compact Advanced Satellite 500-1 (CAS500-1), Korea Multi-Purpose satellite-3 (KOMPSAT-3), PlanetScope, and Sentinel-2A, ships docked within the port berths were visually detected. The berth utilization rate was calculated using the total number of ships that could be docked at the berths. The results showed variations in berth utilization rates on June 2, 2022, with values of 0.67, 0.7, and 0.59, indicating fluctuations based on the time of satellite image capture. On June 3, 2022, the value remained at 0.7, signifying a consistent berth utilization rate despite changes in ship types. A higher berth utilization rate indicates active operations at the berth. This information can assist in basic planning for new ship operation schedules, as congested berths can lead to longer waiting times for ships in anchorages, potentially resulting in increased freight rates. The duration of operations at berths can vary from several hours to several days. The results of calculating changes in ships at berths based on differences in satellite image capture times, even with a time difference of 4 minutes and 49 seconds, demonstrated variations in ship presence. With short observation intervals and the utilization of high-resolution satellite imagery, continuous monitoring within ports can be achieved. Additionally, utilizing satellite imagery to monitor changes in ships at berths in minute increments could prove useful for small and developing country ports where harbor management is not well-established, offering valuable insights and solutions.

• Korean Journal of Remote Sensing
• /
• v.14 no.3
• /
• pp.223-231
• /
• 1998

Ocean Scanning Multispectral Imager (OSMI) is a payload on the Korean Multi-Purpose SATellite (KOMPSAT) to perform worldwide ocean color monitoring for the study of biological oceanography. The instrument images the ocean surface using a whisk-broom motion with a swath width of 800 km and a ground sample distance (GSD) of less than 1 km over the entire field-of-view (FOV). The instrument is designed to have an on-orbit operation duty cycle of 20% over the mission lifetime of 3 years with the functions of programmable gain/offset and on-orbit image data storage. The instrument also performs sun calibration and dark calibration for on-orbit instalment calibration. The OSMI instrument is a multi-spectral imager covering the spectral range from 400 nm to 900 nm using a Charge Coupled Device (CCD) Focal Plane Array (FPA). The ocean colors are monitored using 6 spectral channels that can be selected via ground commands after launch. The instrument performances are fully measured for 8 basic spectral bands centered at 412, 443, 490, 510, 555, 670, 765 and 865 nm during ground characterization of instalment. In addition to the ground calibration, the on-orbit calibration will also be used for the on-orbit band selection. The on-orbit band selection capability can provide great flexibility in ocean color monitoring.