• Korean Journal of Remote Sensing
• /
• v.38 no.6_3
• /
• pp.1777-1788
• /
• 2022

The reservoir is a major water supply source in the domestic agricultural environment, and the monitoring of water storage of reservoirs is important for the utilization and management of agricultural water resource. Remote sensing via satellite imagery can be an effective method for regular monitoring of widely distributed objects such as reservoirs, and in this study, image classification and image segmentation algorithms are applied to Sentinel-1 Synthetic Aperture Radar (SAR) imagery for water body detection in 53 reservoirs in South Korea. Six algorithms are used: Neural Network (NN), Support Vector Machine (SVM), Random Forest (RF), Otsu, Watershed (WS), and Chan-Vese (CV), and the results of water body detection are evaluated with in-situ images taken by drones. The correlations between the in-situ water surface area and detected water surface area from each algorithm are NN 0.9941, SVM 0.9942, RF 0.9940, Otsu 0.9922, WS 0.9709, and CV 0.9736, and the larger the scale of reservoir, the higher the linear correlation was. WS showed low recall due to the undetected water bodies, and NN, SVM, and RF showed low precision due to over-detection. For water body detection through SAR imagery, we found that aquatic plants and artificial structures can be the error factors causing undetection of water body.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.549-554
• /
• 2021

Precise 3D road geospatial information is the basic infrastructure for autonomous driving and is essential data for safe autonomous driving. MMS (Mobile Mapping System) is being used as equipment for road spatial information construction, and related research is being conducted. However, there are insufficient studies to analyze the effect of the baseline reference point distance, which is an important factor in the accuracy of the MMS outcome, on the accuracy of the outcome. Therefore, in this study, the accuracy of the data acquired using MMS by reference point distance was analyzed. Point cloud data was constructed using MMS for the road in the study site. For data processing, 4 data were constructed considering the distance from the reference point for MMS data, and the accuracy was analyzed by comparing the results of 12 checkpoints for accuracy evaluation. The accuracy of the MMS data showed a difference of -0.09 m to 0.11 m in the horizontal direction and 0.04 m to 0.19 m in the height direction. The error in the vertical direction was larger than that in the horizontal direction, and it was found that the accuracy decreased as the distance from the reference point increased. In addition, as the length of the road increases, the distance from the reference point may vary, so additional research is needed. If the accuracy evaluation of the method using multiple reference points is made in the future, it will be possible to present an effective method of using reference points for the construction of precise road spatial information.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.781-791
• /
• 2022

It is crucial to provide forest fire risk forecast information to minimize forest fire-related losses. In this research, forecast models of forest fire risk at a mid-range (with lead times up to 7 days) scale were developed considering past, present and future conditions (i.e., forest fire risk, drought, and weather) through random forest machine learning over South Korea. The models were developed using weather forecast data from the Global Data Assessment and Prediction System, historical and current Fire Risk Index (FRI) information, and environmental factors (i.e., elevation, forest fire hazard index, and drought index). Three schemes were examined: scheme 1 using historical values of FRI and drought index, scheme 2 using historical values of FRI only, and scheme 3 using the temporal patterns of FRI and drought index. The models showed high accuracy (Pearson correlation coefficient >0.8, relative root mean square error <10%), regardless of the lead times, resulting in a good agreement with actual forest fire events. The use of the historical FRI itself as an input variable rather than the trend of the historical FRI produced more accurate results, regardless of the drought index used.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.835-850
• /
• 2022

Microplastics have arisen as a worldwide environmental concern, becoming ubiquitous in all marine compartments, and various researches on monitoring marine microplastics are being actively conducted worldwide. Recently, application of a remote detection technology that enables large-scale real-time observation to marine plastic monitoring has been conducted overseas. However, in South Korea, there is little information linking remote detection to marine microplastics and some field studies have demonstrated remote detection of medium- and large-sized marine plastics. This study introduces research cases with remote detection of marine plastics in South Korea and overseas, investigates potential feasibility of using the remote detection technology to marine microplastic monitoring, and suggests some future works to monitor marine microplastics with the remote detection.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.381-391
• /
• 2022

This paper is intended to find one of the prevailing deep learning models that are a type of AI (Artificial Intelligence) that helps rapidly detect damaged buildings where disasters occur. The models selected are SSD-512, RetinaNet, and YOLOv3 which are widely used in object detection in recent years. These models are based on one-stage detector networks that are suitable for rapid object detection. These are often used for object detection due to their advantages in structure and high speed but not for damaged building detection in disaster management. In this study, we first trained each of the algorithms on xBD dataset that provides the post-disaster imagery with damage classification labels. Next, the three models are quantitatively evaluated with the mAP(mean Average Precision) and the FPS (Frames Per Second). The mAP of YOLOv3 is recorded at 34.39%, and the FPS reached 46. The mAP of RetinaNet recorded 36.06%, which is 1.67% higher than YOLOv3, but the FPS is one-third of YOLOv3. SSD-512 received significantly lower values than the results of YOLOv3 on two quantitative indicators. In a disaster situation, a rapid and precise investigation of damaged buildings is essential for effective disaster response. Accordingly, it is expected that the results obtained through this study can be effectively used for the rapid response in disaster management.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.325-333
• /
• 2021

With the rapidly changing era of the fourth industrial revolution, the utilization of IT technology is increasing. In addition, the demand for security authentication is increasing as shared services or IoT technologies are being developed as new business models. Security authentication is becoming increasingly important for all intelligent devices such as self-driving cars. However, most location-based security authentication technologies are being developed mainly with technologies that utilize server proximity or satellite location tracking, which limits the scope of their physical use. Location-based security authentication technology has recently been developed as a complementary replacement technology. In this study, we introduce location-based security authentication technology using cell broadcasting technology, which has a wider range of applications and is more convenient and business-friendly than existing location-based security authentication technologies. We also introduced application cases and business models related to this. In addition to the current status of technology development, we analyzed current changes in business models being employed. Based on our analysis results, this study draws the implication that technology diversification is necessary to improve the performance of innovative technologies. It is meaningful that it has found and studied advanced technologies other than existing location authentication methods and systems.

• Journal of Korea Water Resources Association
• /
• v.55 no.2
• /
• pp.111-120
• /
• 2022

The concept of soil moisture memory was used as a method for quantifying the function of soil to control water flow, which evaluates the average residence time of precipitation. In order to characterize the soil moisture memory, a new measurement index called stored precipitation fraction (F_p(f)) was used by tracking the increments in soil moisture by the precipitation event. In this study, the temporal and spatial distribution of soil moisture memory was evaluated along with the slope and soil characteristics of the surface (0~5 cm) soil by using satellite- and model-based precipitation and soil moisture in the Korean peninsula, from 2019 to 2020. The spatial deviation of the soil moisture memory was large as the stored precipitation fraction in the soil decreased preferentially along the mountain range at the beginning (after 3 hours), and the deviation decreased overall after 24 hours. The stored precipitation fraction in the soil clearly decreased as the slope increased, and the effect of drainage of water in the soil according to the composition ratio of the soil particle size was also shown. In addition, average soil moisture contributed to the increase and decrease of hydraulic conductivity, and the rate of rainfall transfer to the depths affected the stored precipitation fraction. It is expected that the results of this study will greatly contribute in clarifying the relationship between soil moisture memory and surface characteristics (slope, soil characteristics) and understanding spatio-temporal variation of soil moisture.

• Journal of Korean Society of Forest Science
• /
• v.111 no.4
• /
• pp.603-612
• /
• 2022

The study aims were to evaluate a machine-learning, algorithm-based, forest biomass-estimation model to estimate subnational forest biomass and to comparatively analyze REDD+ forest reference emission levels. Time-series Landsat satellite imagery and ESA Biomass Climate Change Initiative information were used to build a machine-learning-based biomass estimation model. The k-nearest neighbors algorithm (kNN), which is a non-parametric learning model, and the tree-based random forest (RF) model were applied to the machine-learning algorithm, and the estimated biomasses were compared with the forest reference emission levels (FREL) data, which was provided by the Paraguayan government. The root mean square error (RMSE), which was the optimum parameter of the kNN model, was 35.9, and the RMSE of the RF model was lower at 34.41, showing that the RF model was superior. As a result of separately using the FREL, kNN, and RF methods to set the reference emission levels, the gradient was set to approximately -33,000 tons, -253,000 tons, and -92,000 tons, respectively. These results showed that the machine learning-based estimation model was more suitable than the existing methods for setting reference emission levels.

• Journal of Aerospace System Engineering
• /
• v.16 no.4
• /
• pp.28-34
• /
• 2022

In 2021, Virgin Orbit converted a 747-400 aircraft into an air launch platform, and successfully launched it twice in February and July. Compared to the existing ground launch, interest in the air launch is increasing due to its great utility, such as its independence from the launch location or weather, cost reducing factor, shorter launch preparation time, and its benefit pursuant to altitude and speed. Additionally, as small satellites have similar performance to mid/large satellites in the past due to the miniaturization and precision of electronic equipment, small satellite launches are expected to dominate in the future. In this paper, institutional certification methods such as domestic, overseas, civilian and military airworthiness certification regulations/procedures are reviewed to ensure flight safety of aerial projectiles using large domestic civil aircraft, and applicable civil and military airworthiness certification technology standards are reviewed and analyzed. Additionally, we will review and suggest effective airworthiness certification application plans that reflect the reality, and present airworthiness certification standards (draft) for aerial launch vehicles, by analyzing applicable airworthiness certification technical standards when remodeling aerial launch vehicles.