• 한국정보처리학회논문지
• /
• 제4권3호
• /
• pp.859-870
• /
• 1997

컴퓨터에 의한 도면자동입력 시스템은 화상처리 중에서 중요한 응용분야 중에 하나이다.지도 정보의 데이터 베이스는 교통, 행정, 지원개발 및 계획수립 등의 분야 에서 유용하게 활용된다. 그러나 도로정보 추출시, 지도상의 문자나 기타 심벌에 의해 중첩된 영역에서는 도로가 끊어진 채 추출된다. 이러한 각종 심범에 의해 끊어진 도로의 복원에 관한 연구는 거의 이루어지고 있지 않은 실정이다. 본 연구에서는 도로정보와 추출 및 지도 기호에 의해 절단된 도로정보의 복원을 위한 계층적 신경회로망을 제안한다. 본 시스템을 국립지원 발행의 1/25,000지도에 적용하여 그 유효성을 보인다.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2008년도 춘계 종합학술대회 논문집
• /
• pp.449-452
• /
• 2008

레이저 측량기술은 센서와 지표면까지의 거리 및 방향을 관측하여 지표면 상의 표고점에 대한 3차원 좌표를 결정할 수 있으므로 도심지의 건물이 밀집되어 있는 지역이나 산림의 각기 다른 다양한 수종이 분포되어 잇는 곳에서의 정보를 고밀도로 측량하여 파악할 수 가 있다. 새로운 첨단기술로 부각되고 있는 레이져 측량에 의한 고도자료를 기존의 항공사진과 통합하여 고밀도 고정도의 3차원 공간정보를 생성하고 이를 건설 및 환경, 방재 분야에서 활용할 수 있는 활용방안을 도출하고자 한다. 따라서 본 연구에서는 우선 도심공간의 빌딩 및 지형지물에 관한 고밀도의 레이져 측량에 의한 건물의 높이 데이터를 추출하고 이것을 동일지역의 항공사진에 동일한 좌표로 매칭하여 3차원의 도심빌딩을 보다 정확하게 생성하도록 한다. 이러한 통합방법을 도심지의 건물밀집지역 뿐만 아니라 산림지에서의 수종의 분포조사와 하천지역의 3차원 유형조사, 사면경사가 급한 재난 예상 지역조사, 고건축물의 복원등에 적용할 수 있는 다양한 활용기술을 개발하여 실험하였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1397-1399
• /
• 2003

When and Where, What kind of agricultural products will be produced and provided for the market? It is a commercial requirement, and also an academic questions to remote sensing technology. Crop physiology analysis and growth monitoring are important elements for precision agriculture management. Remote sensing technology supplies us more selections and available spaces in this dynamic change study by producing images of different spatial, spectral and temporal resolutions. Especially, the hyperspectral remote sensing should do play a key role in crop growth investigation at national, regional and global scales. In the past five years, Chinese academy of sciences and Japan NTT-DATA have made great efforts to establish a prototype information service system to dynamically survey the vegetable planting situation in Nagano area of Japan mainly based on remote sensing data. For such concern, a flexible and light-duty flight system and some practical data processing system and some necessary background information should be rationally made together. In addition, some studies are also important, such as quick pre-processing for hyperspectral data, Multi-temporal vegetation index analysis, hyperspectral image classification in support of GIS data, etc. In this paper, several spectral data analysis models and a designed airborne platform are provided and discussed here.

• Journal of Korean Neurosurgical Society
• /
• 제41권6호
• /
• pp.371-376
• /
• 2007

Objective : The aim of this study was to investigate the usefulness of diffusion-weighted imaging [DWI] and apparent diffusion coefficiency [ADC] in distinguishing brain abscesses from cystic or necrotic brain tumors, which are difficult to be differentiated by conventional magnetic resonance imaging techniques. Methods : Seven patients with brain abscesses and ten patients with cystic brain tumors were studied from September 2003 to October 2005. Abscess, subdural empyema and ventriculitis were categorized to the abscess group and cystic or necrotic brain gliomas or metastatic brain tumors into the tumor group. Preoperative magnetic resonance images were performed in all patients and diffusion-weighted images and apparent diffusion coefficiency values of lesions were calculated directly from software of 1.5 tesla MRI [General Electrics, USA]. The ratio of the ADC of the lesion to contralateral regional ADC was also measured [relative ADC, rADC]. Results : The average ADC value of pyogenic abscesses group was $0.82+/-0.14{\times}10^{-3}\;[mean+/-S.D.]\;mm^2/s$ and mean rADC was 0.75. Cystic or necrotic areas had high ADC values [$2.49+/-0.79{\times}10^{-3}\;mm^2/s$, mean rADC=2.14]. ADC and rADC values of abscesses group showed about three times lower values than those of cystic or necrotic tumor group. Conclusion : This study results based on numerical comparison of signal intensities and quantitative analysis to distinguish between brain abscess and cystic or necrotic tumor, DWI and ADC mapping are thought to be very useful diagnostic tools.

• 한국항해항만학회지
• /
• 제32권10호
• /
• pp.771-776
• /
• 2008

선박에서 제어판의 역할은 운동을 제어하는데 목적이 있으며 이는 곧 조종성능을 결정하는 중요한 요소이다. 본 연구에서는 플랩타의 성능평가를 위하여 $Re=3.0{\times}10^4$에서 영각에 대응하는 플랩각에 따른 속도 및 에너지 분포를 2-프레임 그레이레벨 상호상관 PIV기법을 이용하여 비교 분석하였다. 또한 영각 10도와 20도에서 전통적인 단동타의 유동특성과 비교하여 플랩타의 성능특성을 평가하였다. 영각 10도에서는 양력, 영각 20도에서는 항력에 의한 측압력을 향상시킬 수 있었다. 영각 10도에서 플랩조작만으로 박리점과 경계층영역의 변화가 가능하였다.

• 대한원격탐사학회지
• /
• 제16권1호
• /
• pp.25-36
• /
• 2000

위성영상으로부터 추출된 선구조가 지질 및 지질구조와 연관되어 해석이 가능한 지 알아보기 위하여 의성소분지에서 추출된 선구조와 지표지질 조사 결과를 비교하였다. 위성영상으로부터 추출된 선구조는 N20$^{\circ}$~30$^{\circ}$E, N60$^{\circ}$~70$^{\circ}$E, N60$^{\circ}$~70$^{\circ}$W의 주방향을 보이며, 이는 단층 주향 및 절리의 방향을 대표한다. 한편 퇴적층내의 선 구조들은 밀양소분지와 의성소분지의 경계인 팔공산융기대를 경계로 이북에서는 북북동, 서북서 방향이, 이남에서는 동북동 방향의 선구조가 우세하게 나타나, 퇴적상을 기준으로 결정된 기존의 경계와 잘 일치한다. 따라서 위성영상을 이용한 선구조는 광역지질구조 및 지표지질 연구에 매우 효과적으로 사용될 수 있다.

• 한국지구과학회지
• /
• 제40권4호
• /
• pp.406-413
• /
• 2019

Red-Green-Blue (RGB) imagery techniques are useful for both forecasters and public users because they are intuitively understood, have advantageous visualization, and do not lose observational information. This study presents a novel RGB convective cloud product and its application to tropical cyclone analysis using Communication, Oceanography, and Meteorology (COMS) satellite observations. The RGB convective cloud product was developed using the brightness temperature differences between WV ($6.75{\mu}m$) and IR1 ($10.8{\mu}m$), and IR2 ($12.0{\mu}m$) and IR1 ($10.8{\mu}m$) as well as the brightness temperature in the IR1 bands of the COMS, with the threshold values estimated from the Korea Meteorological Administration (KMA) radar observations and the EUMETSAT RGB recipe. To verify the accuracy of the convective cloud RGB product, the product was applied to the center positions analysis of two typhoons in 2013. Thus, the convective cloud RGB product threshold values were estimated for WV-IR1 (-20 K to 15 K), IR1 (210 K to 300 K), and IR1-IR2 (-4 K to 2 K). The product application in typhoon analysis shows relatively low bias and root mean square errors (RMSE)s of 23 and 28 km for DANAS in 2013, and 17 and 22 km for FRANCISCO in 2013, as compared to the best tracks data from the Regional Specialized Meteorological Center (RSMC) in Tokyo. Consequently, our proposed RGB convective cloud product has the advantages of high accuracy and excellent visualization for a variety of meteorological applications.

• 대한신경집중치료학회지
• /
• 제11권2호
• /
• pp.86-92
• /
• 2018

Background: A delay of transfer for patients with acute stroke needing emergent revascularization is a huge hurdle for efficacy of revascularization. The objective of this study was to investigate changes of transportation time calculated by image to door (ITD) time (from checking brain images at first contact hospital to arriving at our emergency center) before and after 2015. Methods: This study was performed in a retrospective manner from 2013 into 2017. Acute ischemic stroke (AIS) patients having intravenous thrombolysis and/or mechanical thrombectomy during the observation period were enrolled. Among them, those who had revascularization under 'Drip-and-Ship' or 'Ship-and-Drip' paradigm were selected. Results: During the observation period, 225 patients were treated under 'Drip-and-Ship' or 'Ship-and-Drip' paradigm. Twenty-three were excluded due the lack of detailed data. Among 202 patients, 73 and 129 were treated under Drip-and-Ship and Ship-and-Drip paradigms, respectively. In 2013, 35 patients from 18 hospitals (median distance, 25 km) were transferred to our regional stroke center and their median ITD time was 116 minutes. It was gradually decreased after 2015. In 2017, ITD time was significantly (P<0.01) shortened to 85 minutes without significant changes in transfer distance. The median onset to puncture time was also significantly (P=0.03) decreased from 365 minutes in 2013 to 270 minutes in 2017. Conclusion: Our results implicate that many hospitals in our stroke region might have recognized the importance of rapid transportation for AIS after 2015.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.2086-2097
• /
• 2021

The current cultural assets are being restored depending on the opinions of experts (craftsmen). We intend to introduce digitalized artificial intelligence techniques, excluding the personal opinions of experts on reconstruction of such cultural properties. The first step toward restoring digitized cultural properties is separation. The restoration of cultural properties should be reorganized based on recorded documents, period historical backgrounds and regional characteristics. The cultural properties in the form of photographs or images should be collected by separating the background. In addition, when restoring cultural properties most of them depend a lot on the tendency of the restoring person workers. As a result, it often occurs when there is a problem in the accuracy and reliability of restoration of cultural properties. In this study, we propose a search method for learning stored digital cultural assets using AI technology. Pagoda was selected for restoration of Cultural Properties. Pagoda data collection was collected through the Internet and various historical records. The pagoda data was classified by period and region, and grouped into similar buildings. The collected data was learned by applying the well-known CNN algorithm for artificial intelligence learning. The pagoda search used Yolo Marker to mark the tower shape. The tower was used a total of about 100-10,000 pagoda data. In conclusion, it was confirmed that the probability of searching for a tower differs according to the number of pagoda pictures and the number of learning iterations. Finally, it was confirmed that the number of 500 towers and the epochs in training of 8000 times were good. If the test result exceeds 8,000 times, it becomes overfitting. All so, I found a phenomenon that the recognition rate drops when the enemy repeatedly learns more than 8,000 times. As a result of this study, it is believed that it will be helpful in data gathering to increase the accuracy of tower restoration.

• 대한원격탐사학회지
• /
• 제38권5_1호
• /
• pp.545-557
• /
• 2022

본 연구는 직접적인 접근이 어려운 demilitarized zone (DMZ)의 산불 피해 지역을 파악하기 위하여, 고해상도 위성영상 및 머신러닝 기반의 감독 분류 기법을 이용하였다. 고해상도 위성 영상은 Sentinel-2 A/B를 이용하였으며, SVM 감독분류 기법을 기반으로 토지피복도를 산출하였다. DMZ 산불 피해 지역을 분류하기 위한 최적의 조합을 찾기 위하여 SVM 내에 다양한 커널과 밴드 조합에 따른 감독 분류를 진행하고 오차 행렬을 통해 정확도를 평가하였다. 또한, 2020년, 2021년은 위성영상 자료 기반의 산불 탐지 결과와 산불 연보의 피해 지역 면적 간의 비교를 통한 검증을 수행하였다. 이후, 현재 피해 면적 자료가 없는 2022년의 산불 피해 지역을 탐지함으로써 신뢰할 만한 수준의 결과를 신속적으로 파악하고자 하였다.