• 대한원격탐사학회지
• /
• 제38권6_1호
• /
• pp.1109-1124
• /
• 2022

본 연구에서는 단시간 내 광범위한 지역에 대한 해양쓰레기 발생 실태 파악이 가능하도록 위성 및 드론다중분광 영상을 이용한 해안쓰레기 모니터링 기법을 제안한다. Sentinel-2 위성 영상을 이용한 해안쓰레기 탐지를 위해 multi-layer perceptron (MLP) 모델을 적용하였고, 드론 다중분광 영상을 이용한 해안쓰레기 탐지를 위해 딥러닝 모델 중 U-Net, DeepLabv3+ (ResNet50), DeepLabv3+ (Inceptionv3)의 탐지 성능평가 및 비교를 수행하였다. 위성 영상을 이용한 해안쓰레기 탐지 결과 F1-Score 0.97을 보였다. 드론 다중분광 영상을 이용한 해안쓰레기 탐지는 초목류와 플라스틱류에 대한 탐지를 수행하였고, 탐지 결과 DeepLabv3+ (Inceptionv3) 모델이 mean Intersection over Union (mIoU) 0.68로 가장 우수한 성능을 보였다. 초목류는 F1-Score 0.93, IoU는 0.86을 보인 반면에 플라스틱류의 F1-Score 0.5, IoU는 0.33으로 낮은 성능을 보였다. 그러나 플라스틱류 마스크 영상 생성을 위해 적용된 분광 지수식의 F1-Score는 0.81로 DeepLabv3+ (Inceptionv3)의 플라스틱류 탐지 성능보다 높은 성능을 보이며, 분광 지수식을 이용한 플라스틱류 모니터링이 가능할 것으로 판단된다. 본 연구에서 제안된 해안쓰레기 모니터링 기법을 통해 해안쓰레기 발생에 대한 정량적 자료 제공과 더불어 해안쓰레기 수거·처리 계획 수립에 활용할 수 있다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.618-620
• /
• 2004

This paper explores the use of IKONOS imagery of 1 m resolution panchromatic (PAN) band and 4 m resolution multi-spectral (MS) band in the development of agriculture­related data inventories. Three images (May 25, 2001, December 25, 2001, October 23, 2003) were used to obtain temporal distributions in crop cover characteristics such as rice, pear, grape, red pepper, corn, barley, garlic and surface water cover of reservoir with field investigations. The availability and cost problems are expected to solve by KOMPSAT-2 that is scheduled to launch in 2005. The capability of KOMPSAT-2 image for crop and rural water resources management will increase by accumulating temporal data inventories as a database.

• 대한공간정보학회지
• /
• 제24권2호
• /
• pp.95-106
• /
• 2016

Landslide is one of the natural hazards, triggered by rainfall or earthquake and it leads to damage and loss of properties and lives especially in hilly and mountainous regions. Inventory maps of the area is of much importance in order to understand the landslide phenomena in detail, conduct further studies on landslide, prepare susceptibility map and minimize risk. Inventory maps of landslides can be constructed by several methods, using multiple images through visual interpretation, using algorithms in multi-spectral or SAR images or verification from field investigation. The possible methods were explored for Sindhupalchowk district of Nepal, which was struck by massive earthquake on 2015 and landslide inventory was prepared. The inventory was analyzed for its frequency over elevation, slope aspect and dominant soil classes and also the information value for their occurrence probability.

• 대한원격탐사학회지
• /
• 제21권5호
• /
• pp.425-431
• /
• 2005

This paper describes the method of using IKONOS imagery in the development of agriculture-related data inventories. Temporally different three images of panchromatic (1m resolution) and multi-spectral bands (4m resolution) were used to obtain the distribution and characteristics of rice, pear, grape, red pepper, garlic, and reservoir surface area with the field surveys. The result of this study suggests the utility of KOMPSAT-II, which increases the use of the crop and water resources data in rural areas by accumulating temporal data inventories.

• Korean Journal of Radiology
• /
• 제23권9호
• /
• pp.854-865
• /
• 2022

Photon-counting detector (PCD) CT is a new CT technology utilizing a direct conversion X-ray detector, where incident X-ray photon energies are directly recorded as electronical signals. The design of the photon-counting detector itself facilitates improvements in spatial resolution (via smaller detector pixel design) and iodine signal (via count weighting) while still permitting multi-energy imaging. PCD-CT can eliminate electronic noise and reduce artifacts due to the use of energy thresholds. Improved dose efficiency is important for low dose CT and pediatric imaging. The ultra-high spatial resolution of PCD-CT design permits lower dose scanning for all body regions and is particularly helpful in identifying important imaging findings in thoracic and musculoskeletal CT. Improved iodine signal may be helpful for low contrast tasks in abdominal imaging. Virtual monoenergetic images and material classification will assist with numerous diagnostic tasks in abdominal, musculoskeletal, and cardiovascular imaging. Dual-source PCD-CT permits multi-energy CT images of the heart and coronary arteries at high temporal resolution. In this special review article, we review the clinical benefits of this technology across a wide variety of radiological subspecialties.

• 한국농공학회논문집
• /
• 제47권7호
• /
• pp.3-9
• /
• 2005

A computer system for crop information was developed using Visual Basic and ArcGIS VBA. The system is operated on ArcGIS 8.3 with Microsoft Access MDB. Landsat +ETM, KOMPSAT-1 EOC, ASTER VNIR and IKONOS panchromatic (Pan) and multi-spectral (MIS) images were included in the system to extract agricultural land use items identifiable at various spatial resolutions of images. Agriculture related data inventories using crop cover information such as texture and average pixel value of each band based on crop cultivation calendar were designed and implemented. Three IKONOS images were loaded in the system to show crop cover characteristics such as rice, pear, grape, red pepper, garlic, and surface water cover of reservoir with field surveys. GIS layers such as DEM (Digital Elevation Model), stream, road, soil, land use and administration boundary were prepared to understand the related characteristics and identify the location easily.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권3호
• /
• pp.941-953
• /
• 2012

A novel and universal method of video image text detection is proposed. A coarse-to-fine text detection method is implemented. Firstly, the spectral clustering (SC) method is adopted to coarsely detect text regions based on the stationary wavelet transform (SWT). In order to make full use of the information, multi-parameters kernel function which combining the features similarity information and spatial adjacency information is employed in the SC method. Secondly, 28 dimension classifying features are proposed and support vector machine (SVM) is implemented to classify text regions with non-text regions. Experimental results on video images show the encouraging performance of the proposed algorithm and classifying features.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권4호
• /
• pp.1140-1152
• /
• 2012

A novel and universal method of video image text detection is proposed. A coarse-to-fine text detection method is implemented. Firstly, the spectral clustering (SC) method is adopted to coarsely detect text regions based on the stationary wavelet transform (SWT). In order to make full use of the information, multi-parameters kernel function which combining the features similarity information and spatial adjacency information is employed in the SC method. Secondly, 28 dimension classifying features are proposed and support vector machine (SVM) is implemented to classify text regions with non-text regions. Experimental results on video images show the encouraging performance of the proposed algorithm and classifying features.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1209-1211
• /
• 2003

The wavelet and semivariogram analysis method are used to identify the city landscape and farmland landscape pattern on the 1m resolution IKONOS images. The results prove that wavelet method is a potential way for landscape pattern analysis. Compared to semivariogram analysis, Wavelet analysis can not only detect the overall spatial pattern, but also find multi-scale and direction structures. In this experiment, the wavelet analysis results indicate: (1) the city landscape image is mainly composed of three level structures whose spatial pattern characters appear at 2m, 16m, 128m and 256m accordingly; (2) the farmland landscape is mainly two scale spatial patterns appearing at the 2m, 128m and 256m. IKONOS Remote sensing, with the high spatial and spectral information, is a powerful tool that can use in many ecological systems research and sustainable management.

• 항공우주기술
• /
• 제13권2호
• /
• pp.80-86
• /
• 2014

본 연구에서는 다목적실용위성 3호 영상을 이용하여 지표면 상의 정규식생지수 비교 분석 하고자 한다. 산출된 다목적실용위성 3호의 정규식생지수 비교 분석을 위해 동일 지점 최소 관측 시간 오차를 가지는 고해상도 GeoEye 영상이 사용되었다. 먼저, 각 밴드별 분광 정도 산출을 위해 대기 보정이 수행되었다. 대기 보정 수행을 위한 기하 정보는 다목적실용위성 3호 보조자료에 포함된 태양천정각, 태양방위각, 위성천정각, 위성방위각, 날짜 정보이다. 그리고 대기 요소에 의한 감쇄, 산란, 흡수 정보를 물리적으로 계산하기 위해 수증기량, 오존량, 에어러솔 정보가 적용되었다. 일반적으로 정확한 대기정보를 얻기 위해서는 현장관측자료가 중요하지만, 본 연구에서는 MODIS atmospheric products를 사용하였고, 대기보정 모델에서 산출된 지면 반사도는 식생지수 산출에 사용되었다.