Most Downloaded

  • Research ArticleAugust 31, 2024

    292 69

    Applicability Analysis of Constructing UDM of Cloud and Cloud Shadow in High-Resolution Imagery Using Deep Learning

    Nayoung Kim, Yerin Yun, Jaewan Choi , Youkyung Han

    Korean Journal of Remote Sensing 2024; 40(4): 351-361

    https://doi.org/10.7780/kjrs.2024.40.4.3

    Abstract
    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.
  • Research ArticleJune 30, 2024

    159 67

    Accuracy Assessment of Precipitation Products from GPM IMERG and CAPPI Ground Radar over South Korea

    Imgook Jung, Sungwon Choi, Daeseong Jung, Jongho Woo, Suyoung Sim, Kyung-Soo Han

    Korean Journal of Remote Sensing 2024; 40(3): 269-274

    https://doi.org/10.7780/kjrs.2024.40.3.3

    Abstract
    High-quality precipitation data are crucial for various industries, including disaster prevention. In South Korea, long-term high-quality data are collected through numerous ground observation stations. However, data between these stations are reprocessed into a grid format using interpolation methods, which may not perfectly match actual precipitation. A prime example of real-time observational grid data globally is the Integrated Multi-satellite Retrievals for Global Precipitation Measurement (GPM IMERG) from National Aeronautics and Space Administration (NASA), while in South Korea, ground radar data are more commonly used. GPM and ground radar data exhibit distinct differences due to their respective processing methods. This study aims to analyze the characteristics of GPM and Constant Altitude Plan Position Indicator (CAPPI), representative real-time grid data, by comparing them with ground-observed precipitation data. The study period spans from 2021 to 2022, focusing on hourly data from Automated Synoptic Observing System (ASOS) sites in South Korea. The GPM data tend to underestimate precipitation compared to ASOS data, while CAPPI shows errors in estimating low precipitation amounts. Through this comparative analysis, the study anticipates identifying key considerations for utilizing these data in various applied fields, such as recalculating design rainfall, thereby aiding researchers in improving prediction accuracy by using appropriate data.
  • October 31, 2023

    38 66
    Abstract
    The increasing interest in soil moisture data using satellite data for applications of hydrology, meteorology, and agriculture has led to the development of methods for generating soil moisture maps of variable resolution. This study demonstrated the capability of generating soil moisture maps using Sentinel-1 and Sentinel-2 data provided by Google Earth Engine (GEE). The soil moisture map was derived using synthetic aperture radar (SAR) image and optical image. SAR data provided by the Sentinel-1 analysis ready data in GEE was applied with normalized difference vegetation index (NDVI) based on Sentinel-2 and Environmental Systems Research Institute (ESRI)-based Land Cover map. This study produced a soil moisture map in the research area of Victoria, Australia and compared it with field measurements obtained from a previous study. As for the validation of the applied method’s result accuracy, the comparative experimental results showed a meaningful range of consistency as 4–10%p between the values obtained using the algorithm applied in this study and the field-based ones, and they also showed very high consistency with satellite-based soil moisture data as 0.5–2%p. Therefore, public open data provided by GEE and the algorithm applied in this study can be used for high-resolution soil moisture mapping to represent regional land surface characteristics.
  • Research ArticleDecember 31, 2024

    140 65
    Abstract
    The increasing uncertainty in crop production caused by climate change underscores the necessity of accurate yield predictions for staple crops like rice. This study developed a rice yield prediction model that accounts for climate change by integrating satellite imagery and artificial intelligence. Key variables, including temperature, precipitation, and solar radiation, were derived from Korea Meteorological Administration Automated Synoptic Observing System (ASOS) data and combined with NASA’s Shuttle Radar Topography Mission Digital Elevation Model (SRTM DEM) to incorporate topographic factors. A comprehensive database integrating vegetation indices from Moderate Resolution Imaging Spectroradiometer (MODIS) and Visible Infrared Imaging Radiometer Suite (VIIRS) was established, and Automated Machine Learning (AutoML) was employed to optimize the rice yield prediction model. Validation results demonstrated high predictive accuracy, with the model utilizing ASOS data achieving a MAPE of 4.091% in 2023. This study contributes to data-driven decision-making for climate-resilient agricultural policies and enhanced food security.
  • Research ArticleDecember 31, 2024

    165 65
    Abstract
    The Compact Advanced Satellite 500-4 (CAS500-4) is scheduled for launch in 2025 and is expected to play a significant role in monitoring agricultural and forest resources across the Korean Peninsula. However, the absence of actual CAS500-4 data prior to launch presents challenges for pre-launch research and verification, which constrains the ability to reflect the distinctive attributes of the satellite accurately. To address this issue, this study proposes a method for generating CAS500-4 Level-1 Radiometric (L1R) simulated images by inverse orthorectification based on the rational function model (RFM). Sentinel-2 orthoimages were used as the base image, and rational polynomial coefficients (RPCs) collected from Korea Multi-Purpose Satellite-3A (KOMPSAT-3A) were adjusted and utilized. The objective was to meet the ground sample distance (GSD) requirement of 5 m, consistent with CAS500-4 specifications, and to simulate different viewing angles from the base orthoimage using adjusted RPCs. The results demonstrated that the proposed method established a relationship with the base orthoimage and generated L1R simulated images. These simulated images provide a reliable basis for validating operational processes and preparing for various applications, ensuring effective utilization of CAS500-4 during its early operations.
  • Research ArticleDecember 31, 2024

    77 63

    Analysis of Landslide Damage from Rainfall Using Drone Mapping

    Eontaek Lim , Yonghan Jung , Seul Koo , Seongsam Kim

    Korean Journal of Remote Sensing 2024; 40(6): 1347-1357

    https://doi.org/10.7780/kjrs.2024.40.6.2.6

    Abstract
    This paper proposed an investigation and analysis plan applying drone mapping technology for landslide damage assessment. Traditional landslide investigation methods are limited by accessibility and require significant time and cost, whereas drone-based methods enable rapid data collection and the generation of high-resolution terrain information. Building on this, the research conducted precise analyses of terrain changes, affected areas, and the scale of damage in landslide-prone regions. It visually represented the characteristics of the damaged areas using 3D models and point clouds, confirming the potential for a more quantitative assessment of the damage extent. This paper suggests that the findings could be effectively utilized for future landslide damage investigations and recovery planning.
  • ReviewOctober 31, 2024

    1162 63

    National Disaster Management and Monitoring Using Satellite Remote Sensing and Geo-Information

    Jongsoo Park , Hagyu Jeong , Junwoo Lee

    Korean Journal of Remote Sensing 2024; 40(5): 813-832

    https://doi.org/10.7780/kjrs.2024.40.5.2.9

    Abstract
    As disasters become more diverse and widespread, disaster management at the national level is increasingly important. Since satellite remote sensing technology is capable of observing a wide range of areas on a regular basis, it can be effectively utilized to monitor a massive scale of disaster conditions and preemptively respond to urgent disasters. Disasters that can be managed through satellite remote sensing technology include forest fires, drought, floods, landslides, and earthquakes. This study introduces a variety of studies using satellite remote sensing and Geographic Information System (GIS) as well as a number of actual cases utilizing the above. However, with the satellites currently in operation, there are difficulties in detecting and analyzing the disasters above due to the limitations on spatial and temporal resolutions. Recently, new measures have been developed to overcome such limitations through the development and constellation operation of microsatellites. In addition, new technologies are under development where a massive quantity of satellite images is analyzed by Artificial Intelligence (AI) technology. It is expected that temporal and spatial limitations can be addressed through satellite-developed and constellation systems in the future, which would lead to scientific disaster management through grafting with AI technology.
  • Research ArticleDecember 31, 2024

    109 60

    Dataset Construction and Semantic Segmentation of Buildings and Roads from CAS500-1 Images

    Riwon Kim, Hongjong Oh, Suyoung Park, Hyojin Yang, Yangwon Lee

    Korean Journal of Remote Sensing 2024; 40(6): 1163-1176

    https://doi.org/10.7780/kjrs.2024.40.6.1.23

    Abstract
    The current status of buildings and roads is an essential element of land monitoring and management, and is used in various fields such as urban planning, disaster management, and change detection. With the recent advancement of deep learning technology, high-performance semantic segmentation techniques have become commonplace, and research on applying them to building and road detection has begun to be actively conducted. However, most of these studies are conducted overseas, so there are still limitations in applying them to Korean field. Therefore, in this study, we constructed a building and road detection dataset optimised for Korea using high-resolution Compact Advanced Satellite (CAS500) images and digital maps, and developed a detection model using the latest semantic segmentation models, the unified perceptual parsing network (UPerNet) based on the sifted window (Swin) transformer and the masked-attention mask transformer (Mask2Former), and compared and evaluated their performance. In particular, a systematic refinement process was used to minimise the spatiotemporal discrepancies between the satellite imagery and the digital maps, and a temporary dataset consisting of only pure digital map labels was created separately to evaluate the effectiveness of the dataset built in this way. The results of the building and road detection experiments showed that the Mask2Former model using the Swin-L backbone performed the best with a building intersection over union (IoU) of 77.93 and a road IoU of 74.85. In addition, the model trained with the optimised dataset in this study performed qualitatively and quantitatively better than the model trained with the pure digital map dataset, proving its effectiveness. The methodology and results of this study are expected to contribute to the efficiency of land status information construction and monitoring in Korea, and furthermore, it is expected that it can serve as a practical basis for the advancement of land spatial information services and the establishment of related policies.
  • Research ArticleFebruary 28, 2024

    98 58

    Multi-Class Multi-Object Tracking in Aerial Images Using Uncertainty Estimation

    Hyeongchan Ham , Junwon Seo, Junhee Kim, Chungsu Jang

    Korean Journal of Remote Sensing 2024; 40(1): 115-122

    https://doi.org/10.7780/kjrs.2024.40.1.11

    Abstract
    Multi-object tracking (MOT) is a vital component in understanding the surrounding environments. Previous research has demonstrated that MOT can successfully detect and track surrounding objects. Nonetheless, inaccurate classification of the tracking objects remains a challenge that needs to be solved. When an object approaching from a distance is recognized, not only detection and tracking but also classification to determine the level of risk must be performed. However, considering the erroneous classification results obtained from the detection as the track class can lead to performance degradation problems. In this paper, we discuss the limitations of classification in tracking under the classification uncertainty of the detector. To address this problem, a class update module is proposed, which leverages the class uncertainty estimation of the detector to mitigate the classification error of the tracker. We evaluated our approach on the VisDrone-MOT2021 dataset, which includes multi-class and uncertain far-distance object tracking. We show that our method has low certainty at a distant object, and quickly classifies the class as the object approaches and the level of certainty increases. In this manner, our method outperforms previous approaches across different detectors. In particular, the You Only Look Once (YOLO)v8 detector shows a notable enhancement of 4.33 multi-object tracking accuracy (MOTA) in comparison to the previous state-of-the-art method. This intuitive insight improves MOT to track approaching objects from a distance and quickly classify them.
  • Research ArticleDecember 31, 2024

    164 55
    Abstract
    Semantic image segmentation techniques have recently gained widespread adoption in the field of remote sensing for tasks such as classifying surface properties and extracting specific objects. The performance of semantic image segmentation is influenced not only by the choice of deep learning model but also by the configuration of key hyperparameters, including learning rate and batch size. Among these hyperparameters, the batch size is typically set to a larger value to improve model performance. However, since the processing capacity of a typical deep learning system’s graphics processing unit (GPU) is limited, selecting an appropriate batch size is necessary. This paper investigates the impact of batch size on building detection performance in deep learning systems for semantic image segmentation using satellite and aerial imagery. For the performance analysis, representative models for semantic image segmentation, including UNet, ResUNet, DeepResUNet, and CBAM-DRUNet, were used as baseline models. Additionally, transfer learning models such as UNet-VGG19, UNet-ResNet50, and CBAM-DRUNet-VGG19 were incorporated for comparison. The training datasets used in this study included the WHU and INRIA datasets, which are commonly used for semantic image segmentation tasks, as well as the Kompsat-3A dataset. The experimental results revealed that a batch size of 2 or larger led to an improvement in F1 scores across all models and datasets. For the WHU dataset, the smallest of the datasets, the F1 score initially increased with batch size, but after reaching a certain threshold, it began to decline, except for the CBAM-DRUNet-VGG19 model. In contrast, for the INRIA dataset, which is approximately 1.5 times larger than WHU, transfer learning models maintained relatively stable F1 scores as the batch size increased, while other models showed a similar trend of increasing F1 scores followed by a decrease. In the case of the Kompsat-3A datasets, which are 4 to 5 times larger than the WHU dataset, all models showed a substantial increase in F1 score when the batch size was set to 2. Beyond this point, F1 scores stabilized without further significant improvements. In terms of training time, increasing the batch size generally resulted in reduced training time for all models. Therefore, when the training dataset is sufficiently large, setting the batch size to 2 is already sufficient to achieve significant improvements in F1 score accuracy. Furthermore, setting the batch size to a value greater than 2 may be advantageous in terms of further reducing training time, provided that the GPU capacity of the deep learning system is sufficient to handle the larger batch size.
KSRS
December 2024 Vol. 40, No. 6, pp. 881-1521

Most Keyword ?

What is Most Keyword?

  • It is the most frequently used keyword in articles in this journal for the past two years.

Most View

Editorial Office

Korean Journal of Remote Sensing