• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.381-391
• /
• 2022

This paper is intended to find one of the prevailing deep learning models that are a type of AI (Artificial Intelligence) that helps rapidly detect damaged buildings where disasters occur. The models selected are SSD-512, RetinaNet, and YOLOv3 which are widely used in object detection in recent years. These models are based on one-stage detector networks that are suitable for rapid object detection. These are often used for object detection due to their advantages in structure and high speed but not for damaged building detection in disaster management. In this study, we first trained each of the algorithms on xBD dataset that provides the post-disaster imagery with damage classification labels. Next, the three models are quantitatively evaluated with the mAP(mean Average Precision) and the FPS (Frames Per Second). The mAP of YOLOv3 is recorded at 34.39%, and the FPS reached 46. The mAP of RetinaNet recorded 36.06%, which is 1.67% higher than YOLOv3, but the FPS is one-third of YOLOv3. SSD-512 received significantly lower values than the results of YOLOv3 on two quantitative indicators. In a disaster situation, a rapid and precise investigation of damaged buildings is essential for effective disaster response. Accordingly, it is expected that the results obtained through this study can be effectively used for the rapid response in disaster management.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2019.11a
• /
• pp.243-245
• /
• 2019

In the VTS, the predictions of vessel mobility and situation awareness of maritime environment are basic function. In recent years, pilotage information is an essential aware element of VTS personnel for vessel traffic management. So, we designed the structure of pilotage information service with VTS and tested in real environment. In the future, similar pilotage information can be used as a useful VTS service.

• Electronics and Telecommunications Trends
• /
• v.30 no.5
• /
• pp.28-38
• /
• 2015

최근 빈번히 발생하고 있는 도심지 내 지반침하의 주된 원인은 지하공간의 난개발, 상하수도 시설의 노후화, 이로 인한 급격한 지하 수위의 변화에 기인한다고 알려져 있으며 이에 대한 실시간 모니터링 및 종합적인 상관성 분석을 통한 사고예방이 시급한 실정이다. 지하공간의 특수성으로 인해 광역 지하공간 정보를 실시간으로 수집하여 모니터링할 수 있는 기술이 부재한 점과 이로 인한 지하공간의 위험도 분석과 과학적 재난대응 시스템 구축에 어려움이 존재한다. 본고에서는 도시 지하공간 내 지하매설물(상하수도)의 상태와 지하공간상황(도시철도구조물, 지하수, 지반변형)을 실시간으로 모니터링하기 위한 도메인별 기술개발 동향에 대해서 정리하고, 수집된 정보의 종합적 분석을 통한 지하공간의 이상 징후를 사전감지, 예측, 대응하기 위해 도전하고 있는 기술적 이슈들을 살펴보고자 한다.

• Journal of the Society of Disaster Information
• /
• v.11 no.4
• /
• pp.556-569
• /
• 2015

With about 75% of the population of Korea criticizing the government's disaster policy and a failure to respond to large-scale emergency like the Sewol ferry sinking means that there is a deep distrust in the government. In order to prevent dreadful disasters such as the Sewol ferry sinking, it is important to secure a prime time with respect to disaster safety. Improving crisis management skills and managerial role of police officers who are in close proximity to the people is necessary for the success of disaster management. With disaster management as one of the most essential missions of the police, as a part of a national crisis management, a step by step strengthening of the disaster safety management system of the police is necessary, as below. First, at the prevention phase, law enforcement officers were not injected into for profit large-scale assemblies or events, but in the future the involvement, injection should be based on the level of potential risk, rather than profitability. In the past and now, the priortiy was the priority was on traffic flow, traffic communication, however, the paradigm of traffic policy should be changed to a safety-centered policy. To prevent large-scale accidents, police investigators should root out improper routines and illegal construction subcontracting. The police (intelligence) should strengthen efforts to collect intelligence under the subject of "safety". Second, with respect to the preparatory phase, on a survey of police officers, the result showed that 72% of police officers responded that safety management was not related to the job descriptions of the police. This, along with other results, shows that the awareness of disaster safety must be adopted by, or rather changed in the police urgently. The training in disaster safety education should be strengthened. A network of experts (private, administrative, and police) in safety management should be established to take advantage of private resources with regard to crisis situtions. Third, with respect to the response phase, for rapid first responses to occur, a unified communication network should be established, and a real-time video information network should be adopted by the police and installed in the police situation room. Fourth, during the recovery phase, recovery teams should be injected, added and operated to minimize secondary damage.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.372-372
• /
• 2020

사회가 다원화되고 발달하면서 생활환경과 행동양식에 따라 홍수 등의 수난(水難) 으로 인한 피해 정도와 양상은 크게 달라질 수 있으나, 수난으로 인한 체감 가능한 피해의 정도와 규모는 예측이 어려운 현실이다. 그리고, 최근 인터넷과 소셜 네트워크 서비스(SNS)의 급진적 발달은 재난 관리에 대중적 지식을 수집하여 활용하도록 촉진하고 있고, 이로 인해 재난 상황에서 '대중적인 정보가 기술자에 의해 어떻게 얼마나 신중하게 고려되어야 하는지와 어떻게 과학적으로 해석해야하는지'가 핵심 쟁점으로 부상하고 있다. 본 연구에서는 최근 널리 사용되는 인공지능 및 딥러닝 기법을 조사 분석하였다. 분석을 통해 수문 예측 분야에서 이러한 기술이 적용된 사례와 신기술을 조망해 보고 기존 기술이 인공지능 및 딥러닝 기법의 적용으로 대체 가능한 정도를 가늠해 보았다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.295-298
• /
• 2014

In recently, a climatic change(such as subtropical climate and frequent unusual high temperature) and the open-trade policies of agricultural & livestock products are increasing the outbreak risk of highly pathogenic avian influenza(HPAI) and foot and mouth disease(FMD), and accordingly the socio-economic damage and impacts are also increasing due to the cases such as damage from the last 5 times of FMD outbreak(3,800 billion won), from 10 years public control cost of Pine Wilt Disease (PWD)(238.3 billion won), and from the increased invasive pests of exotic plant like isoptera. Therefore, the establishment of new operation strategy of IoT(Internet of Things) based satellite early warning system(SEWS) for plants and animals as a subsystem of national disaster response and management system is being required, where the forensic technology & measures should be applied as a government policy to estimate the post compensation and to carry out the legal responsibility.

• Journal of Korea Water Resources Association
• /
• v.54 no.1
• /
• pp.61-69
• /
• 2021

In this study, in order to efficiently perform smart city river management, we developed an integrated platform that connects flood analysis models on the web and provides information by converting input and output data into a database. In the integrated platform, a watershed analysis model, a river flow analysis model and an urban runoff analysis model were applied to perform flood analysis in smart city. This platform is able to obtain more reliable results by step-by-step approach to urban runoff that may occur in smart city through the applied model. In addition, since all analysis processes such as data collection, input data generation and result storage are performed on the web, anyone in an environment that can access the web without special equipment or tools can perform analysis and view results. Through this, it is expected that smart city managers can efficiently manage urban runoff and nearby rivers, and can also be used as educational materials for urban outflows.

• The Journal of the Korea Contents Association
• /
• v.15 no.2
• /
• pp.377-392
• /
• 2015

In today's data-driven society, we've been hearing a great deal about the power of Big Data over the last couple of years. At the same time, it has become the most important issue that the problems is caused by the data collection, management and utilization. Moreover, Big Data has a wide applications ranging from situation awareness, decision-making to the area to enable for the foreseeable future with man-made and analysis of data. It is necessary to process data into meaningful information given that the huge amount of structured and unstructured data being created in the private and the public sector, even in disaster management. This data should be public and private sector at the same time for the appropriate linkage analysis for effective disaster management. In this paper, we conducted a literature review and case study efficient Big Data to derive the revitalization of national disaster management. The study obtained data on the role and responsibility of the public sector and the private sector to leverage Big Data for promotion of national disaster management plan. Both public and private sectors should promote common development challenges related to the openness and sharing of Big Data, technology and expansion of infrastructure, legal and institutional maintenance. The implications of the finding were discussed.

• Journal of Advanced Navigation Technology
• /
• v.16 no.2
• /
• pp.271-277
• /
• 2012

In this paper, we propose a dynamic tree formation protocol for multiple UAV which is gathering data or accomplishing a mission such as disaster monitoring, environment monitoring, and disaster relief. Especilly, we designed Hop-LQI Weight algorithm to form optimal tree in wireless dynamic environment applying situation of radio signal attenuation over distance and implemented our algorithm in MSP 430 K-mote sensor platform using TinyOS codes. We verified performance of our algorithm by comparing average link setup time by the number of nodes with minimum LQI, link cost calculation method in wireless communication.

• Journal of the Korea Convergence Society
• /
• v.9 no.8
• /
• pp.25-32
• /
• 2018

Recently, the size and type of disasters in Korea has been diversified. However, Korea has not been able to build various information support systems to predict these disasters.Many other organizations also provide relevant information. This information is mainly provided on the Web, but most of it is not real time information. In this study, we have paid attention to support information using big data to provide better quality real - time information together with information provided by institutions. Big data has a large amount of information with real-time property, and it can make customized service using it. Among them, SNS such as Twitter and Facebook can be used as a new information collection medium in case of disaster. However, it is very difficult to retrieve necessary information from too much information, and it is difficult to collect intuitive information. For this purpose, this study develops an information support system using Twitter. The system retrieves information using the Twitter hashtag. Also, information mapping is performed on the map so that intuitive information can be grasped. For system evaluation, information extraction, degree of mapping, and recommendation speed are evaluated.