• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.343-346
• /
• 2019

This letter describes a development of satellite-based forest withering index for detection of fire burn area and its application to the Goseong-Sokcho and Gangneung-Donghae wildfires in April 4, 2019. Withered forest has very different spectral characteristics from healthy forest. In particular, a false color composite of R-NIR-G represents such difference very clearly. Using Sentinel-2 images with the forest withering index, we derived the area burned by the wildfires: approximately 701.16 ha for Goseong-Sokcho and approximately 710.60 ha for Gangneung-Donghae, although official record will be announced by the Korean government later.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.431-447
• /
• 2021

Recently, the use of high-resolution satellites is increasing in many areas. In order to supply useful satellite images stably, it is necessary to establish automatic precision geometric correction technic. Geometric correction is the process that corrected geometric errors of satellite imagery based on the GCP (Ground Control Point), which is correspondence point between accurate ground coordinates and image coordinates. Therefore, in the automatic geometric correction process, it is the key to acquire high-quality GCPs automatically. In this paper, we proposed iterative precision geometry correction method. we constructed an image pyramid and repeatedly performed GCP chip matching, outlier detection, and precision sensor modeling in each layer of the image pyramid. Through this method, we were able to acquire high-quality GCPs automatically. we then improved the performance of geometric correction of high-resolution satellite images. To analyze the performance of the proposed method, we used KOMPSAT-3 and 3A Level 1R 8 scenes. As a result of the experiment, the proposed method showed the geometric correction accuracy of 1.5 pixels on average and a maximum of 2 pixels.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1357-1369
• /
• 2022

Cloud removal is an essential image processing step for any task requiring time-series optical images, such as vegetation monitoring and change detection. This paper presents a two-stage cloud removal method that combines conditional generative adversarial networks (cGANs) with regression-based calibration to construct a cloud-free time-series optical image set. In the first stage, the cGANs generate initial prediction results using quantitative relationships between optical and synthetic aperture radar images. In the second stage, the relationships between the predicted results and the actual values in non-cloud areas are first quantified via random forest-based regression modeling and then used to calibrate the cGAN-based prediction results. The potential of the proposed method was evaluated from a cloud removal experiment using Sentinel-2 and COSMO-SkyMed images in the rice field cultivation area of Gimje. The cGAN model could effectively predict the reflectance values in the cloud-contaminated rice fields where severe changes in physical surface conditions happened. Moreover, the regression-based calibration in the second stage could improve the prediction accuracy, compared with a regression-based cloud removal method using a supplementary image that is temporally distant from the target image. These experimental results indicate that the proposed method can be effectively applied to restore cloud-contaminated areas when cloud-free optical images are unavailable for environmental monitoring.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1315-1328
• /
• 2022

Sinduri beach is a typical sedimentary landform that forms sand dunes due to the influence of the northwest wind in winter. Due to the its large scale and well-developed nature, it has been recognized for conservation value and is currently designated as Natural Monument No. 431, and continuous monitoring is required in terms of the preservation of topographical values. In this study, aerial images, drone images, and drone-based LiDAR data during 36 years were used for long-term topographical change observation of the Sinduri coastal sand dunes located in Taean-gun, Chungcheongnam-do. To implement this, the amount of change in elevation and volume for each period was calculated by applying the difference of Digital Elevation Model (DEM) based on raster calculation using the numerical elevation model generated from the raw data. Also, the amount of change in volume based on probability was calculated using the error propagation law for the intrinsic error of each data source. As a result, it can be seen that from 1986 to 2022, deposition of 35,119 m³ occurred in region of interest A (area: 17,960 m²) and 54,954 m³ of deposition occurred in region of interest B (area: 17,686 m²).

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1245-1255
• /
• 2022

Terra Nova Bay polynya (TNBP) is a representative coastal polynya in East Antarctica, which is formed by strong katabatic winds. As the TNBP is one of the major sea ice factory in East Antarctica and has a great impact on regional ocean circulation and surrounding marine ecosystem, it is very important to analyze its area change and development characteristics. In this study, we detected the TNBP from synthetic aperture radar (SAR) and optical images obtained from April 2007 to April 2022 by visually analyzing the stripes caused by the Langmuir circulation effect and the boundary between the polynya and surrounding sea ice. Then, we analyzed the area change and development characteristics of the TNBP. The TNBP occurred frequently but in a small size during the Antarctic winter (April-July) when strong katabatic winds blow, whereas it developed in a large size in March and November when sea ice thickness is thin. The 12-hour mean wind speed before the satellite observations showed a correlation coefficient of 0.577 with the TNBP area. This represents that wind has a significant effect on the formation of TNBP, and that other environmental factors might also affect its development process. The direction of TNBP expansion was predominantly determined by the wind direction and was partially influenced by the local ocean current. The results of this study suggest that the influences of environmental factors related to wind, sea ice, ocean, and atmosphere should be analyzed in combination to identify the development characteristics of TNBP.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.979-989
• /
• 2022

We examined changes in the shell valve movements (SVMs) of Mytilus edulis and Crassostrea gigas using a Hall element sensor to investigate the early detection of the toxic dinoflagellate Alexandrium pacificum. No increase or decrease was observed in SVMs caused by the non-toxic algae Isochrysis galbana in both M. edulis and C. gigas. However, when M. edulis and C. gigas were exposed to A. pacificum, which causes paralytic shellfish poisoning, the average SVMs for 12 hours before and after exposure increased from 1.25 times/hr to 2.13 times/hr and 2.23 times/hr to 8.91 times/hr, respectively. After exposure to A. pacificum, the SVMs of M. edulis increased rapidly within 1 hour and then decreased gradually. However, C. gigas showed high SVMs until 4 hours after exposure. SVMs of C. gigas appeared to be more sensitive to toxic dinoflagellate than those of M. edulis. Therefore, these results are expected to be used as basic data for the establishment of a biological monitoring system for early detection of the toxic dinoflagellate A. pacificum.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.913-924
• /
• 2022

In this paper, we presented a database construction of undersea images for the Habitats of Ecklonia cava and Sargassum and conducted an experiment for semantic segmentation using state-of-the-art (SOTA) models such as High Resolution Network-Object Contextual Representation (HRNet-OCR) and Shifted Windows-L (Swin-L). The result showed that our segmentation models were superior to the existing experiments in terms of the 29% increased mean intersection over union (mIOU). Swin-L model produced better performance for every class. In particular, the information of the Ecklonia cava class that had small data were also appropriately extracted by Swin-L model. Target objects and the backgrounds were well distinguished owing to the Transformer backbone better than the legacy models. A bigger database under construction will ensure more accuracy improvement and can be utilized as deep learning database for undersea images.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.695-706
• /
• 2022

Medium and high-resolution optical satellites have proven their effectiveness in detecting wildfire areas. However, smoke plumes generated by wildfire scatter visible light incidents on the surface, thereby interrupting accurate monitoring of the area where wildfire occurs. Therefore, a technology to extract smoke in advance is required. Deep learning technology is expected to improve the accuracy of smoke extraction, but the lack of training datasets limits the application. However, for clouds, which have a similar property of scattering visible light, a large amount of training datasets has been accumulated. The purpose of this study is to develop a smoke extraction technique using deep learning, and the limits due to the lack of datasets were overcome by using a cloud dataset on transfer learning. To check the effectiveness of transfer learning, a small-scale smoke extraction training set was made, and the smoke extraction performance was compared before and after applying transfer learning using a public cloud dataset. As a result, not only the performance in the visible light wavelength band was enhanced but also in the near infrared (NIR) and short-wave infrared (SWIR). Through the results of this study, it is expected that the lack of datasets, which is a critical limit for using deep learning on smoke extraction, can be solved, and therefore, through the advancement of smoke extraction technology, it will be possible to present an advantage in monitoring wildfires.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.211-220
• /
• 2021

Land Surface Temperature (LST) is one of the useful parameters to diagnose the growth and development of crop and to detect crop stress. Unmanned Aerial Vehicle (UAV)-based LST (LSTUAV) can be estimated in the regional spatial scale due to miniaturization of thermal infrared camera and development of UAV. Given that meteorological variable, type of instrument, and surface condition can affect the LSTUAV, the evaluation for accuracy of LSTUAV is required. The purpose of this study is to evaluate the accuracy of LSTUAV using LST measured at ground (LSTGround) under various meteorological conditions and growth phases of garlic crop. To evaluate the accuracy of LSTUAV, Relative humidity (RH), absolute humidity (AH), gust, and vegetation index were considered. Root mean square error (RMSE) after minimizing the bias between LSTUAV and LSTGround was 2.565℃ under above 60% of RH, and it was higher than that of 1.82℃ under the below 60% of RH. Therefore, LSTUAV measurement should be conducted under the below 60% of RH. The error depending on the gust and surface conditions was not statistically significant (p-value < 0.05). LSTUAV had reliable accuracy under the wind speed conditions that allow flight and reflected the crop condition. These results help to comprehend the accuracy of LSTUAV and to utilize it in the agriculture field.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_2
• /
• pp.875-883
• /
• 2023

In this letter, we used PlanetScope imagery to conduct experiments on the color characteristics for oil type classification of marine oil spills through Red-Green-Blue (RGB) histogram analysis. The histograms of marine oil spills can be divided into three categories (dark black tones, light silver tones, and light rainbow tones) according to the distribution of pixel values in each band. Thick oil layers with dark black tones can be classified as heavy oil, while thin oil layers with light silver and rainbow tones can be classified as light oil. As more images are analyzed in the future, these oil spill detection and classification methods will become more generalized and reliable.