• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.840-843
• /
• 2006

The aim of this study was to detect landslide using satellite image and apply the landslide to probabilistic landslide-susceptibility mapping at Gangneung area, Korea using a Geographic Information System (GIS). Landslide locations were identified by change detection technique of KOMSAT-1 (Korea Multipurpose Satellite) EOC (Electro Optical Camera) images and checked in field. For landslide-susceptibility mapping, maps of the topography, geology, soil, forest, lineaments, and land cover were constructed from the spatial data sets. Then, the sixteen factors that influence landslide occurrence were extracted from the database. Using the factors and detected landslide, the relationships were calculated using frequency ratio, one of the probabilistic model. Then, landslide-susceptibility map was drawn using the frequency ration and finally, the map was verified by comparing with existing landslide locations. As the verification result, the prediction accuracy showed 86.76%. The landslide-susceptibility map can be used to reduce hazards associated with landslides and to land cover planning.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.567-569
• /
• 2006

Recently, the terrestrial laser scanner is considered as useful measurement equipment for acquiring a three-dimensional data. In this study, a terrestrial laser scanner which has +/- 2.5cm accuracy is examined whether the terrestrial laser scanner is reliable to present the tendency of landslide movement. The test area is covered by protection blocks, and they are being moved by landslide movement. Landslide movement was detected by measuring the movement of protection blocks. Totally three scenes of test area were acquired during 2004 and 2006. The three scenes of the protection blocks were registered in global coordinate system, then the landslide movement was investigated. The landslide movement detected in the three scenes was evaluated by comparing with landslide movement measured by a total station. Although the measurement accuracy of landslide using the terrestrial laser scanner was worse than the total station, the scanning data showed the tendency of landslide movement of the test area.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.233-235
• /
• 2005

This paper presents an unsupervised change detection methodology designed for the detection of landslide areas. The proposed methodology consists of two analytical steps: one for multi-temporal segmentation and the other for automatic selection of thresholding values. By considering the conditions of landslide occurrences and the spectral behavior of multi-temporal remote sensing images, some specific procedures are included in the analytical steps mentioned above. The effectiveness and applicability of the methodology proposed here were illustrated by a case study of the Gangneung area, Korea. The case study demonstrated that the proposed methodology could detect about $83\%$ of landslide occurrences.

• 대한원격탐사학회지
• /
• 제34권4호
• /
• pp.591-600
• /
• 2018

Recent SAR systems provide fully polarimetric SAR data, which is known to be useful in a variety of applications such as disaster monitoring, target recognition, and land cover classification. The objective of this study is to evaluate the performance of polarization SAR data for landslide detection. The detectability of different SAR parameters was investigated based on the supervised classification approach. The classifier used in this study is the Adaptive Boosting algorithms. A fully polarimetric L-band PALSAR-2 data was used to examine landslides caused by the 2016 Kumamoto earthquake in Kyushu, Japan. Experimental results show that fully polarimetric features from the target decomposition technique can provide improved detectability of landslide site with significant reduction of false alarms as compared with the single polarimetric observables.

• 대한원격탐사학회지
• /
• 제34권1호
• /
• pp.45-74
• /
• 2018

Landslide is a natural hazard that threats lives and properties in many areas around the world. Landslides are difficult to recognize, particularly in rainforest regions. Thus, an accurate, detailed, and updated inventory map is required for landslide susceptibility, hazard, and risk analyses. The inconsistency in the results obtained using different features selection techniques in the literature has highlighted the importance of evaluating these techniques. Thus, in this study, six techniques of features selection were evaluated. Very-high-resolution LiDAR point clouds and orthophotos were acquired simultaneously in a rainforest area of Cameron Highlands, Malaysia by airborne laser scanning (LiDAR). A fuzzy-based segmentation parameter (FbSP optimizer) was used to optimize the segmentation parameters. Training samples were evaluated using a stratified random sampling method and set to 70% training samples. Two machine-learning algorithms, namely, Support Vector Machine (SVM) and Random Forest (RF), were used to evaluate the performance of each features selection algorithm. The overall accuracies of the SVM and RF models revealed that three of the six algorithms exhibited higher ranks in landslide detection. Results indicated that the classification accuracies of the RF classifier were higher than the SVM classifier using either all features or only the optimal features. The proposed techniques performed well in detecting the landslides in a rainforest area of Malaysia, and these techniques can be easily extended to similar regions.

• 자원환경지질
• /
• 제52권4호
• /
• pp.313-322
• /
• 2019

SAR (Synthetic Aperture Radar) 원격탐사 관측 자료는 폭우나 태풍으로 인해 넓은 지역에 걸쳐 발생할 수 있는 산사태 피해 지역을 신속하게 탐지하는데 매우 유용한 도구이다. 본 연구의 목적은 산사태 발생 이후에 관측이 수행된 다중 편광 SAR 자료를 이용하여 산사태 지역을 자동으로 분류하는 효과적인 알고리즘을 개발하는 것이다. 실험적인 분석을 바탕으로 SAR 관측 자료로부터 산사태를 탐지하기 위해서는 SAR 영상의 스펙클 현상을 줄여주는 스펙클 필터와 경사진 지형에서의 기하왜곡을 보정하는 정사보정이 필수적임을 확인하였고, IDAN 필터를 적용하여 스펙클을 줄이고 다중 편광 파라미터를 추정한 후에 정사보정을 수행하는 것이 산사태 탐지를 위해 적합한 처리 과정임을 제시하였다. 또한 다양한 다중 편광 파라미터에 대한 탐지 성능 분석을 통해 entropy 파라미터가 산사태 탐지에 좋은 성능을 보임을 파악하였다. 이러한 분석을 토대로 다중 편광 파라미터에 대한 자동적인 문턱값 설정과 DEM을 보조적으로 사용하는 산사태 탐지 알고리즘을 제안하였다. 탐지 알고리즘은 2011년 9월 태풍 탈라스에 의해 발생한 산사태에 대해 관측을 수행한 ALOS-2위성의 PALSAR-2 자료를 이용하여 실험적인 평가를 수행하였고, 약 82%의 탐지율과 3%의 오경보율로 산사태를 탐지 할 수 있음을 확인하였다.

• 한국정보통신설비학회:학술대회논문집
• /
• 한국정보통신설비학회 2008년도 정보통신설비 학술대회
• /
• pp.262-267
• /
• 2008

Recently, landslides frequently occur on natural slope and/or man-made cut slope during periods of intense rainfall. With a rapidly increasing population on or near steep terrain, landslides have become one of the most significant natural hazards. Thus, it is necessary to protect people from landslides and to minimize the damage of houses, roads and other facilities. To accomplish this goal, many landslide monitoring systems have been developed throughout the world. In this paper, a simple landslide detection system that enables people to escape the endangered area is introduced. The system is focused on the debris flows which happen frequently during periods of intense rainfall. The system is based on the wireless sensor network (WSN) that is composed of wireless sensor nodes, gateway, and remote server system. Wireless sensor nodes and gateway are deployed by commercially available Microstrain G-Link products. Five wireless sensor nodes and one gateway are installed at the test slope for detecting ground movement. The acceleration and inclination data of test slope can be obtained, which provides a potential to detect landslide. In addition, thresholds to determine whether the test slope is stable or not are suggested by a series of numerical simulations, using geotechnical analysis software package. It is obtained that the alarm should be issued if the x-direction displacement of sensor node is greater than 20mili-meters and the inclination of sensor node is greater than 3 degrees. It is expected that the landslide detection method using wireless senor network can provide early warning where landslides are prone to occur.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2010년 춘계학술발표회 논문집
• /
• pp.379-380
• /
• 2010

GIS has the basic ability to process high-dense and precise digital data like LiDAR. But the software that common users can use when necessary is expensive and practically impossible for actual use. Thus this study set out to research the methodologies to process and service time series LiDAR data for landslide monitoring.

• 지질공학
• /
• 제24권4호
• /
• pp.615-629
• /
• 2014

본 연구는 자연사면 산사태를 대상으로 한 실시간 모니터링 기술과 이를 이용한 산사태 탐지기술에 대해 기존 특허를 체계적으로 분석하였다. 특허분석의 목적은 산사태재해 관련 기술 동향을 파악하고 이를 토대로 보다 진보된 기술을 개발하는데 활용하기 위한 것이다. 이 분석에서는 산사태 모니터링 및 탐지기술에 관련된 특허를 한국, 미국, 일본, 중국(홍콩), 유럽, 대만 등 총 6개의 국가를 대상으로 하여 주요 키워드 별로 검색하였다. 대분류와 소분류로 나누어 각각 기술 분류에 따라 연도별, 국가별, 출원인별 분석을 실시하였으며, 분석결과에 따라 국가별 요소기술 및 유망기술에 대한 포트폴리오를 도출하였다. 본 연구의 분석결과는 향후 산사태 모니터링 및 탐지기술 분야에 있어서 더욱 효과적인 연구 개발 방향을 수립하고, 기존의 기술과 차별화된 연구 성과를 이끌어 내는데 도움이 될 수 있는 기초 자료가 될 수 있을 것으로 사료된다.

• 대한원격탐사학회지
• /
• 제26권1호
• /
• pp.47-57
• /
• 2010

본 연구의 목적은 2006년 태풍 에위니아, 빌리스, 개미와 집중호우로 인해 많은 산사태가 발생한 진부면 지역을 대상으로 항공사진을 이용한 산사태 탐지 및 인공신경망과 GIS를 이용한 산사태 취약성을 분석하는데 있다. 산사태 위치는 산사태 발생 전후의 항공사진을 판독 후 현장에서 확인하였다. 취약성 분석을 위해 지형, 지질, 토양, 임상, 선구조, 토지이용도 등의 자료는 공간 데이터베이스로 구축하였다. 산사태와 관련 요인들간의 상대적 가중치는 인공신경망의 역전파 알고리즘을 이용하여 결정하였다. 그 결과 경사방향과 경사는 다른 요인들 보다 1.2~1.5배 높게 나타났다. 이 가중치를 이용하여 취약성도를 작성 후 분석에 사용하지 않은 산사태 위치와 비교하여 검증하였다. 그 결과 예측 정확도는 81.44%로 나타났다.