• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1451-1466
• /
• 2023

In the context of maritime emergencies, the utilization of drones has rapidly increased, with a particular focus on their application in search and rescue operations. Deep learning models utilizing drone images for the rapid detection of distressed vessels and other maritime drift objects are gaining attention. However, effective training of such models necessitates a substantial amount of diverse training data that considers various weather conditions and vessel states. The lack of such data can lead to a degradation in the performance of trained models. This study aims to enhance the performance of deep learning models for distress ship detection by developing a maritime environment simulator to augment the dataset. The simulator allows for the configuration of various weather conditions, vessel states such as sinking or capsizing, and specifications and characteristics of drones and sensors. Training the deep learning model with the dataset generated through simulation resulted in improved detection performance, including accuracy and recall, when compared to models trained solely on actual drone image datasets. In particular, the accuracy of distress ship detection in adverse weather conditions, such as rain or fog, increased by approximately 2-5%, with a significant reduction in the rate of undetected instances. These results demonstrate the practical and effective contribution of the developed simulator in simulating diverse scenarios for model training. Furthermore, the distress ship detection deep learning model based on this approach is expected to be efficiently applied in maritime search and rescue operations.

• Journal of Convergence for Information Technology
• /
• v.10 no.9
• /
• pp.147-153
• /
• 2020

As demand for drone test flight is rapidly increasing, it is difficult for Goheung Aviation Center alone to meet the test flight demand. Newly developed drones or modified existing aircraft carry potential flight risks due to unpredictable flight performance or poor pilot skill when performing test flights outside the test site. Therefore, it is necessary to ensure sufficient test flight space for the safety verification of manned and unmanned aircraft. Therefore, this study analyzed the status of domestic flight test site and chapter 5 of ICAO DOC 9184-AN / 902 Part 1 (Airport Planning Manual). And to build a comprehensive flight test infrastructure, the methodology for preliminary evaluation of candidate sites for flight test sites and a method for evaluating infrastructure test sites was presented.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.12
• /
• pp.899-907
• /
• 2022

According to the Unmanned aircraft system Traffic Management (UTM), drones are permitted to fly up to 150m above ground, which is located in the atmospheric boundary layer where there is considerable wind fluctuation due to turbulence. Although it is difficult to predict when turbulence will occur drone aviation safety could be enhanced by having a better understanding of the characteristics of vertical profile of wind in the flight area. We used wind lidar (WIndMast 350M) to observe vertical profiles of wind at the test site for aviation meteorological observation equipment located near Incheon International Airport in July and September, 2022. In this study, we utilized the observed wind profile data to propose a technique for obtaining information that could help improve the drone aviation safety. The Fourier transform analysis is used to evaluate the temporal characteristics of the horizontal wind speed at various vertical levels up to 350m. We also examined the relative contribution of the variance of wind having scales of less than an hour, a crucial scale for drone flight, to the variance of wind having all scales at each vertical altitude for days with and without precipitation.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.161-161
• /
• 2020

최근 기후변화와 여름철 고온 등으로 인한 녹조현상, 화학물질 및 유류 유출 등 화학사고로 인한 하천의 수질오염과 관련된 사회적 관심이 높아지고 있다. 특히, 화학사고로 인한 유해화학물질 유출은 인체에 접촉 시 악영향을 끼치며, 대기·수질·토양을 오염시키고 주변 농작물의 변색이나 괴사를 유발하는 등의 피해를 야기하기 때문에 적절한 조치와 대응이 필요하다. 환경부에서는 유해화학물질 유출사고로 인한 국민건강 및 환경상의 위해를 예방하기 위해 화학물질관리법과 화학물질 등록 및 평가에 관한 법률을 제정하여 유해화학물질을 관리하고 화학사고에 대응하고 있다. 그러나, 화학사고 발생 시 공장 인근의 먼지, 악취 등을 감시하기 위해 현장인력에 의존하거나 화학물질의 유출이 우려되는 곳에 제한적으로 검출센서를 설치해 사고를 감시하고 있어 검출센서 미설치 지역에 대한 능동적 탐지가 어렵고, 화학물질의 공간적 분포 탐지가 불가능하여 초동 대응에 한계가 있다. 한편 최근 초분광 영상을 활용하여 물질 고유의 분광특성을 분석함으로써 토지피복, 식생, 수질 등의 식별에 활용되고 있다. 따라서 초분광 센서를 활용한 화학물질 감지 가능성도 보여주고 있지만, 초분광 센서를 활용한 하천의 화학물질 감지를 위한 연구는 미비한 실정이다. 이에 본 연구에서는 유해화학물질 18종을 대상으로 초분광 영상을 이용한 상호 구분이 가능한 지 확인하고자 해당 유해화학물질의 초분광 영상을 촬영하여 분광라이브러리를 구축하였다. 또한 물질별 특성을 보이는 분광밴드의 범위를 지정해 특성 분광라이브러리를 구축하였으며, 해당 과정에 대한 표준 및 절차를 제시하였다. 본 연구에서 제시한 절차에 따라 18종의 유해화학물질 분광라이브러리와 특성 분광라이브러리를 구축한 결과, 유해화학물질의 식별 가능성을 확인하였다. 향후 연구를 통해 유해화학물질 분광라이브러리 데이터베이스를 확대하고, 실시간 모니터링에 적용할 경우 신속한 화학사고 발생여부 감지 및 대응에 활용할 수 있을 것으로 사료된다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.688-689
• /
• 2022

This paper proposes the development of an AI drone equipped with motion detection and thermal imaging camera to quickly rescue people from drowning accidents. Currently, when a drowning accident occurs, a large number of manpower must be put in to find the person who needs it, such as conducting a search operation. The time required for this process is too long, and especially the night search is more difficult for a person to do directly. To solve this situation, we are going to use AI drones.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.197-199
• /
• 2020

태풍이나 갑작스러운 기후변화와 같은 돌발 상황이 발생하면 첫째, 그늘막을 일일이 찾아 접어야 하고, 둘째, 안전사고가 발생하지 않도록 안내방송을 해야 하고, 셋째, 접거나 펼칠 때 사람들이 다치지 않도록 경광등을 켜야 하고, 넷째, 그늘막 손상 사건에 대한 뺑소니를 처리해야 하는 등을 해결하는 GRS를 설계한다. GRS는 첫째, 30~500여 개의 컨트론러에 그룹형 자동 개폐 명령 기법을 개발하고 둘째, 30~500여 개의 컨트론러에 그룹형 안내방송기법 및 그늘막 개폐 시 주위에 사람 있는지 확인하여 안전사고 예방 기법 개발을 통해 그늘막의 관리 효용성을 높이고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.928-929
• /
• 2023

도로 교통 사고 및 교통 정체는 도로 상황의 비정상적인 요인으로 인해 발생하는 심각한 문제이다. 이러한 문제를 해결하기 위해 도로 상황을 실시간으로 감지하고 사용자에게 알리는 시스템이 필요하다고 판단된다. 본 연구는 도로 상황 감지 및 예방을 위한 새로운 접근 방식을 제안하며, 이에 대한 배경과 필요성, 그리고 프로젝트의 특장점을 소개한다.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.7
• /
• pp.519-527
• /
• 2017

The trust issue on the safety of autonomous vehicle is a very important in regard to the demand generation of relevant industries. To secure the trust, The study of legal liability issue should be prior to an accident of the autonomous vehicle. In civil law, it is possible to make the automobile manufacturer take legal responsibility with the "Product Liability Act". Whereas, in criminal law, it is difficult to make him take legal responsibility since the criminal law holds the actor responsible. To solve these problems, this article proposes the establishment of the "Special Act on Autonomous Vehicle". Also, there is a demand for building infra structures and system to operate the (fully) self-propelled vehicle and establishing "certification" systems.

• Journal of Convergence for Information Technology
• /
• v.11 no.1
• /
• pp.136-142
• /
• 2021

Open-pit mine development requires continuous management because of topographical changes and there is a risk of accidents if the current status survey is performed directly in the process of calculating the earthwork. In this study, the application of UAV photogrammetry, which can acquire spatial information without direct human access, was applied to open-pit mines development area and analyzed the accuracy, earthwork, and mountain restoration plan to determine its applicability. As a result of accuracy analysis at checkpoint using ortho image and Digital Surface Model(DSM) by UAV photogrammetry, Root Mean Square Error(RMSE) is 0.120 m in horizontal and 0.150 m in vertical coordinates. This satisfied the tolerance range of 1:1,000 digital map. As a result of the comparison of the earthwork, UAV photogrammetry yielded 11.7% more earthwork than the conventional survey method. It is because UAV photogrammetry shows more detailed topography. And result of monitoring mountain restoration showed possible to determine existence of rockfall prevention nets and vegetation. If the terrain changes are monitored by acquiring images periodically, the utility of UAV photogrammetry will be further useful to open-pit mine development.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.3
• /
• pp.257-262
• /
• 2019

Recently, with a great deal of attention and utilization to the UAV like a drone, many application cases using UAV in various fields have been proliferated rapidly. These UAV, however, has many risks like balance deviation and drone crash due to the external environmental factors. The attitude control algorithm for UAV is the most important portion in order to maintain the safe management of UAV, and the best solution is PID control algorithm which is generously used and almost perfect attitude control technology nowadays. In this paper, we propose the smart attitude control algorithm using fuzzy logic in order to provide safe and continuous attitude control against external environmental factors, and compare the performance through simulation study between PID and our algorithm.