• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.359-359
• /
• 2023

최근 기후변화로 인한 홍수 및 가뭄과 같은 자연재해가 증가함에 따라 이를 선제적으로 탐지 및 예방할 수 있는 해결책에 대한 필요성이 증가하고 있다. 이러한 수재해를 예방하기 위해서 하천, 저수지 등 가용수자원의 지속적인 모니터링은 필수적이다. SAR 위성 영상의 경우 주야간 및 기상상황에 상관없이 지속적인 수체 탐지가 가능하다. 일반적으로 SAR 기반 수체 탐지 시 송수신 방향이 동일한 편파(co-polarized) 영상을 사용한다. 하지만 co-polarized 영상의 경우 바람 및 강우에 민감하게 반응하여 수체 미탐지의 가능성이 존재한다. 한편 송수신 방향이 서로 다른 편파(cross-polarized) 영상은 강우 및 바람의 영향에 민감하지 않지만 식생에 민감하게 반응하여 수체의 오탐지율이 높다는 단점이 존재한다. 이에 SAR 영상의 편파 특성에 따라 수체 탐지의 정확도 차이가 발생하여 최적의 편파 영상 조합을 구성하는 것이 중요하다. 본 연구에서는 Sentinel-1 SAR 위성의 VV, VH, VV+VH 편파 영상과 머신러닝 알고리즘 중 하나인 SVM (support vector machine)을 활용하여 수체탐지를 수행하였다. 편파 영상 조합별 수체 탐지 결과의 검증을 위하여 혼동행렬 (confusion matrix) 기반 평가지수를 사용하였다. 각각의 수체탐지 결과의 비교 및 분석을 통하여 SAR 기반 수체 탐지를 위한 최적의 밴드 조합을 도출하였다. 본 연구결과를 바탕으로 차후 높은 시공간 해상도를 가진 SAR 영상의 활용이 가능하다면 수재해 및 수자원 관리의 효율성을 높일 수 있을 것으로 기대된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.2-2
• /
• 2023

기후변화가 가속화로 인해 수재해의 빈도와 강도 예측이 어려워짐에 따라 실시간 홍수 모니터링에 대한 수요가 증가하고 있다. 합성개구레이다는 광원과 날씨에 무관하게 촬영이 가능하여 수재해 발생시에도 영상을 확보할 수 있다. 합성개구레이다를 활용한 수체 탐지 알고리즘 개발이 활발히 연구되어 왔고, 딥러닝의 발달로 CNN을 활용하여 높은 정확도로 수체 탐지가 기능해졌다. 하지만, CNN 기반 수체 탐지 모델은 훈련시 높은 정량적 정확성 지표를 달성하여도 추론 후 정성적 평가시 경계와 소하천에 대한 탐지 정확성이 떨어진다. 홍수 모니터링에서 특히 중요한 정보인 경계와 좁은 하천에 대해서 정확성이 떨어짐에 따라 실생활 적용이 어렵다. 이에 경계를 강화한 적대적 학습 기반의 수체 탐지 모델을 개발하여 더 세밀하고 정확하게 탐지하고자 한다. 적대적 학습은 생성적 적대 신경망(GAN)의 두 개의 모델인 생성자와 판별자가 서로 관여하며 더 높은 정확도를 달성할 수 있도록 학습이다. 이러한 적대적 학습 개념을 수체 탐지 모델에 처음으로 도입하여, 생성자는 실제 라벨 데이터와 유사하게 수체 경계와 소하천까지 탐지하고자 학습한다. 반면 판별자는 경계 거리 변환 맵과 합성개구레이다 영상을 기반으로 라벨데이터와 수체 탐지 결과를 구분한다. 경계가 강화될 수 있도록, 면적과 경계를 모두 고려할 수 있는 손실함수 조합을 구성하였다. 제안 모델이 경계와 소하천을 정확히 탐지하는지 판단하기 위해, 정량적 지표로 F1-score를 사용하였으며, 육안 판독을 통해 정성적 평가도 진행하였다. 기존 U-Net 모델이 탐지하지 못하던 영역에 대해 제안한 경계 강화 적대적 수체 탐지 모델이 수체의 세밀한 부분까지 탐지할 수 있음을 증명하였다.

• Korean Journal of Remote Sensing
• /
• v.32 no.5
• /
• pp.539-550
• /
• 2016

Detection of water bodies in land surface is an essential part of disaster monitoring, such as flood, storm surge, and tsunami, and plays an important role in analyzing spatial and temporal variation of water cycle. In this study, a quantitative comparison of different thresholding-based methods for water body detection and their applicability to Kompsat-5 SAR data were presented. In addition, the effect of speckle filtering on the detection result was analyzed. Furthermore, the variations of threshold values by the proportion of the water body area in the whole image were quantitatively evaluated. In order to improve the binary classification performance, a new water body detection algorithm based on the bimodality test and the majority filtering is presented.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1371-1388
• /
• 2023

Floods are becoming more severe and frequent due to global warming-induced climate change. Water disasters are rising in Korea due to severe rainfall and wet seasons. This makes preventive climate change measures and efficient water catastrophe responses crucial, and synthetic aperture radar satellite imagery can help. This research created 1,423 water body learning datasets for individual water body regions along the Han and Nakdong waterways to reflect domestic water body properties discovered by Sentinel-1 satellite radar imagery. We created a document with exact data annotation criteria for many situations. After the dataset was processed, U-Net, a deep learning model, analyzed water body detection results. The results from applying the learned model to water body locations not involved in the learning process were studied to validate soil water body monitoring on a national scale. The analysis showed that the created water body area detected water bodies accurately (F1-Score: 0.987, Intersection over Union [IoU]: 0.955). Other domestic water body regions not used for training and evaluation showed similar accuracy (F1-Score: 0.941, IoU: 0.89). Both outcomes showed that the computer accurately spotted water bodies in most areas, however tiny streams and gloomy areas had problems. This work should improve water resource change and disaster damage surveillance. Future studies will likely include more water body attribute datasets. Such databases could help manage and monitor water bodies nationwide and shed light on misclassified regions.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.793-810
• /
• 2022

Synthetic Aperture Radar (SAR) is considered to be suitable for near real-time inundation monitoring. The distinctly different intensity between water and land makes it adequate for waterbody detection, but the intrinsic speckle noise and variable intensity of SAR images decrease the accuracy of waterbody detection. In this study, we suggest two modules, named 'morphology module' and 'edge-enhanced module', which are the combinations of pooling layers and convolutional layers, improving the accuracy of waterbody detection. The morphology module is composed of min-pooling layers and max-pooling layers, which shows the effect of morphological transformation. The edge-enhanced module is composed of convolution layers, which has the fixed weights of the traditional edge detection algorithm. After comparing the accuracy of various versions of each module for U-Net, we found that the optimal combination is the case that the morphology module of min-pooling and successive layers of min-pooling and max-pooling, and the edge-enhanced module of Scharr filter were the inputs of conv9. This morphologic and edge-enhanced U-Net improved the F1-score by 9.81% than the original U-Net. Qualitative inspection showed that our model has capability of detecting small-sized waterbody and detailed edge of water, which are the distinct advancement of the model presented in this research, compared to the original U-Net.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.3
• /
• pp.113-127
• /
• 2015

Recently, there has been a growing interest in UAS(Unmanned Aerial System), and it is required to develop techniques to effectively detect water body from the recorded images in order to implement flood monitoring using UAS. This study used a UAS with RGB and NIR+RG bands to achieve images, and applied supervised classification method to evaluate the accuracy of water body detection. Firstly, the result for accuracy in water body image classification by RGB images showed high Kappa coefficients of 0.791 and 0.783 for the artificial neural network and minimum distance method respectively, and the maximum likelihood method showed the lowest, 0.561. Moreover, in the evaluation of accuracy in water body image classification by NIR+RG images, the magalanobis and minimum distance method showed high values of 0.869 and 0.830 respectively, and in the artificial neural network method, it was very low as 0.779. Especially, RGB band revealed errors to classify trees or grasslands of Songsan amusement park as water body, but NIR+RG presented noticeable improvement in this matter. Therefore, it was concluded that images with NIR+RG band, compared those with RGB band, are more effective for detection of water body when the mahalanobis and minimum distance method were applied.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1207-1214
• /
• 2021

In thisletter, we developed technology which can exclude effect of cloudsto perform remote waterbody detection based on Sentinel-2 optical satellite imagery to calculate the area of ungauged reservoirs and applied to the Hwanggang dam reservoir, a representative ungauged reservoir, to verify usability. The remote waterbody detection technology calculates the cloud blocking ratio by comparing the cloud boundary in the Sentinel-2 imagery and the reservoir boundary first. Next, itselects data whose cloud blocking ratio does not exceed a specific value and calculates NDWI (Normalized Difference Water Index) with selected imagery. In last, it calculatesthe area of the reservoir by counting the number of grids which have NDWI value considered as waterbody within the boundary of the target reservoir and correcting with cloud blocking ratio. To determine cloud blocking ratio threshold forselecting image, we performed the area calculation of Hwanggang dam reservoir from July 2018 to October 2021. As a result, when the cloud blocking ratio threshold wasset 10%, we confirmed that the result with large error due to clouds were filtered well and obtained 114 results that can show changes in Hwanggang dam reservoir area among 220 images.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.444-444
• /
• 2023

하천 및 저수지와 같은 공간의 수체 탐지는 수자원 관리에서 매우 중요하며, 유역의 수문학적 과정을 이해하는데 도움을 준다. 수문학적 데이터 수집은 우량계, 수위계와 같은 물리적 인프라의 배치가 필요하다. 그러나 상대적으로 저개발된 국가는 수문학적 측정을 위한 인프라가 매우 미흡한 것이 현실이며, 북한과 같은 비접근 지역에 대한 수문학적 과정을 분석하는데는 한계가 있다. 인공위성 원격탐사 센서 중 SAR영상은 지표면에 직접 전파를 방사하고 산란되어 돌아오는 신호를 수신하여 영상을 만들기 때문에 일반적인 광학영상과는 달리 햇빛의 유무와 강우, 구름여부 등의 기상 조건의 영향을 거의 받지 않는 장점이 있다. 또한 국내와 같이 계절적인 요인과 인간활동에 의해 변화되는 물 순환을 SAR 영상은 지표수의 계절적 및 연간 변동성을 모니터링하는데 매우 유용한 자료로 평가되고 있다. 본 연구는 SAR영상을 이용하여 국내의 검증 가능한 지역의 저수지 수면적 변화를 모니터링하고 저수지 수면적과 저수량 분석을 수행하는 것을 목적으로 하였다. 분석자료인 SAR영상은 ESA의 Sentinel-1영상을 2022년 4월부터 2022년 11월의 자료를 수집하여 소양강댐 저수지 수면적과 저수량과의 관계식을 도출하였다. 수체 추출을 위한 SAR 영상은 특히 수로의 일부 가장자리와 홍수터의 식물 존재로 인한 제외지의 매핑에 부정확성을 포함하여 처리에 몇 가지 단점을 갖는 한계도 존재하지만 악천후의 기상 조건에서도 작동할 수 있는 SAR 영상의 능력 덕분에 규칙적인 시간 간격으로 수체면적의 변화에 대한 정보를 제공할 수 있다. 향후 북한 지역의 주요 댐 저수지 수면적에 대한 연간변화와 장기간의 추세를 분석하는 연구를 진행할 계획이다.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.901-912
• /
• 2022

The frequency of disasters is increasing due to global climate change, and unusual heavy rains and rainy seasons are occurring in Korea. Periodic monitoring and rapid detection are important because these weather conditions can lead to drought and flooding, causing secondary damage. Although research using optical images is continuously being conducted to determine the waterbody, there is a limitation in that it is difficult to detect due to the influence of clouds in order to detect floods that accompany heavy rain. Therefore, there is a need for research using synthetic aperture radar (SAR) that can be observed regardless of day or night in all weather. In this study, using Sentinel-1 SAR images that can be collected in near-real time as open data, the UNet model among deep learning algorithms that have recently been used in various fields was applied. In previous studies, waterbody detection studies using SAR images and deep learning algorithms are being conducted, but only a small number of studies have been conducted in Korea. In this study, to determine the applicability of deep learning of SAR images, UNet and the existing algorithm thresholding method were compared, and five indices and Sentinel-2 normalized difference water index (NDWI) were evaluated. As a result of evaluating the accuracy with intersect of union (IoU), it was confirmed that UNet has high accuracy with 0.894 for UNet and 0.699 for threshold method. Through this study, the applicability of deep learning-based SAR images was confirmed, and if high-resolution SAR images and deep learning algorithms are applied, it is expected that periodic and accurate waterbody change detection will be possible in Korea.

• Journal of Korea Water Resources Association
• /
• v.57 no.3
• /
• pp.181-193
• /
• 2024

The increasing atmospheric imbalance caused by climate change leads to an elevation in precipitation, resulting in a heightened frequency of flooding. Consequently, there is a growing need for technology to detect and monitor these occurrences, especially as the frequency of flooding events rises. To minimize flood damage, continuous monitoring is essential, and flood areas can be detected by the Synthetic Aperture Radar (SAR) imagery, which is not affected by climate conditions. The observed data undergoes a preprocessing step, utilizing a median filter to reduce noise. Classification techniques were employed to classify water bodies and non-water bodies, with the aim of evaluating the effectiveness of each method in flood detection. In this study, the Otsu method and Support Vector Machine (SVM) technique were utilized for the classification of water bodies and non-water bodies. The overall performance of the models was assessed using a Confusion Matrix. The suitability of flood detection was evaluated by comparing the Otsu method, an optimal threshold-based classifier, with SVM, a machine learning technique that minimizes misclassifications through training. The Otsu method demonstrated suitability in delineating boundaries between water and non-water bodies but exhibited a higher rate of misclassifications due to the influence of mixed substances. Conversely, the use of SVM resulted in a lower false positive rate and proved less sensitive to mixed substances. Consequently, SVM exhibited higher accuracy under conditions excluding flooding. While the Otsu method showed slightly higher accuracy in flood conditions compared to SVM, the difference in accuracy was less than 5% (Otsu: 0.93, SVM: 0.90). However, in pre-flooding and post-flooding conditions, the accuracy difference was more than 15%, indicating that SVM is more suitable for water body and flood detection (Otsu: 0.77, SVM: 0.92). Based on the findings of this study, it is anticipated that more accurate detection of water bodies and floods could contribute to minimizing flood-related damages and losses.