• 한국통신학회논문지
• /
• 제39B권10호
• /
• pp.645-653
• /
• 2014

최근 해양 플랜트, 해저 탐사, 수중 모니터링 시스템 등에 대한 관심이 급증하고 있으며, 그에 대한 연구도 활발히 진행 중이다. 하지만, 수중 무선 통신은 물속이라는 특수한 환경적 요소로 인해 지상에 비해 매우 열악한 통신 환경을 가진다. 이로 인해 기존에 사용하던 지상 통신의 방법을 수중에 그대로 적용하는 것은 성능적인 면에서 적합하지 않다. 이에 본 논문은 수중 무선 센서네트워크에서 통신 신뢰성을 향상시키기 위하여 수중 환경의 특성을 직접적으로 고려한 라우팅 알고리즘을 제시한다. 특히, 수중 무선 통신을 어렵게 만드는 두 가지 문제, 즉, 다중경로 문제와 신호의 감쇠현상을 해결함으로써 수중에서 보다 나은 신뢰성을 보장하고자 한다. 또한, 실험을 통하여 제시하는 알고리즘이 보다 나은 성능을 보임을 증명하였다.

• 전기전자학회논문지
• /
• 제27권3호
• /
• pp.225-233
• /
• 2023

본 논문은 해양사고 시 인체 인양정보를 모니터링하는 시스템을 구현한다. 모니터링 시스템은 수중환경 정보를 송신하는 인양기구제어기를 통하여 초음파 통신을 수행하며, 수상에서는 관제센터 또는 모선까지 10 km내 GPS 정보를 제공하기 위해 LoRa 통신을 수행한다. 수중 인양제어기는 공압 센서, 자이로 센서 및 온도센서 정보를 전송한다. 수중조건은 수심 10m 마다 수압 1기압씩 높아지고, 기구의 공기양은 육상에 비해서 1/2씩 줄어드는 환경에서 60 kg 수중 마네킹을 모델을 사용한다. 인양기구 SMB(Surface Marker Buoy)에 38g의 CO2 카트리지 1개를 사용하여 10 sec 이내에 수면 상승 조건을 기반으로 인양기구 출수 시험을 한다. 수중 통신은 수심 40m에서 100m까지 2,400bps 초음파 센서를 이용하여 데이터 전송환경을 구성한다. 모니터링 신호는 수심, 수온, 방향각 등을 수면 위의 구조요원에게 제공함으로써 인양작업자의 안전과 안전한 인체 구조를 목표로 한다.

• 한국해양공학회지
• /
• 제34권3호
• /
• pp.227-236
• /
• 2020

Underwater acoustics, which is the domain that addresses phenomena related to the generation, propagation, and reception of sound waves in water, has been applied mainly in the research on the use of sound navigation and ranging (SONAR) systems for underwater communication, target detection, investigation of marine resources and environment mapping, and measurement and analysis of sound sources in water. The main objective of remote sensing based on underwater acoustics is to indirectly acquire information on underwater targets of interest using acoustic data. Meanwhile, highly advanced data-driven machine-learning techniques are being used in various ways in the processes of acquiring information from acoustic data. The related theoretical background is introduced in the first part of this paper (Yang et al., 2020). This paper reviews machine-learning applications in passive SONAR signal-processing tasks including target detection/identification and localization.

• 한국소음진동공학회논문집
• /
• 제25권11호
• /
• pp.747-752
• /
• 2015

Underwater radiated noise is an important characteristic in the naval weapon systems. It is difficult to measure the radiation efficiency of underwater vehicle, such as UUV(unmanned underwater vehicle) and underwater weapons in real operation environment. In this study, acoustic radiation efficiency of a circular cylindrical structure is measured in the laboratory-water tank. The radiation efficiency is compared with the numerical results and it is found that they are in a good agreement. Therefore, the measurement method can be applied effectively for predicting the underwater radiation noise and effectiveness of radiation reduction means.

• 한국군사과학기술학회지
• /
• 제15권5호
• /
• pp.586-593
• /
• 2012

The Navy is in the process of developing a sonar-operation strategy to increase the effectiveness of underwater target searching capability. HMS is the basic strategy to detect underwater targets. The advantages of HMS is that, it has a short preparation time to operate and can be always used regardless of sea conditions and weather. However, it is difficult to effectively detect underwater targets due to the interaction between marine environments and sonar-operations. During the research, the effectiveness of the HMS system's underwater target searching capability was analyzed by integrating various search and defense patterns, and environment conditions into the simulation. In the simulation the ship search an evasive target within a set region. The simulation presented results for an effective searching and defense methods of underwater targets. These research results can be used as foundation for advancing and improving the sonar operational tactics.

• 한국산업융합학회 논문집
• /
• 제21권6호
• /
• pp.389-394
• /
• 2018

Remotely operated vehicle(ROV) and autonomous underwater vehicle(AUV) have been used for underwater surveys, underwater exploration, resource harvesting, offshore plant maintenance and repair, and underwater construction. It is hard for people to work in the deep sea. Therefore, we need a vision control system of underwater submersible that can replace human eyes. However, many people have difficulty in developing a deep-sea image control system due to the deep sea special environment such as high pressure, brine, waterproofing and communication. In this paper, we will develop an Ethernet based remote image control system that can control the image mounted on ROV.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2013년도 추계학술발표대회
• /
• pp.486-488
• /
• 2013

In the earth more than half of the space filled with water. In that water most of the part is in the form of oceans. The ocean atmosphere determines climate on the land. Combining the Underwater Acoustic Sensor Network (UWASN) system with Internet Of Things (IoT) is called Internet of Underwater Things (IoUT). Using IoUT we can find the changes in the ocean environment. Underwater sensor nodes are used in UWASN. Underwater sensor nodes are constructive in offshore investigation, disaster anticipation, data gathering, assisted navigation, pollution checking and strategic inspection. By using IoT components such as Database, Server and Internet, ocean data can be broadcasted. This paper introduces IoUT architecture and and explains fish forming application scenario with this IoUT architecture.

• 대한임베디드공학회논문지
• /
• 제16권4호
• /
• pp.129-136
• /
• 2021

River facilities and port structures require a regular inspection and diagnosis due to obsolescence. Currently, most river facilities are undergoing indirect inspection and diagnosis by divers. The underwater inspections are not feasible due to safety issues of divers and restrictions on working hours and environment. To overcome these issues, it is intended to conduct inspections of river facilities using underwater drones. In this research, an underwater ROV (Remote Operated Vehicle) has been developed, which is a kind of drone with propellers. As a key device of this research, an injection device has been attached to the underwater drone to conduct an operation test, a stable operation test of an underwater drone, and a test of attached sensors. The river facility inspection can be carried out optimally using the hovering control of the drone and injection systems. With the developed ROV system, hovering test and injection test have been performed to verify the feasibility of this development.

• 한국전자통신학회논문지
• /
• 제1권1호
• /
• pp.27-35
• /
• 2006

가상 해저 환경 속에서 군중 행동은 영화, 게임 등의 엔터테인멘트 산업에서 많은 장면으로 연출된다. 컴퓨터 그래픽스 기술의 발달로 인하여 디지털 영화나 애니메이션이 점차 증가함에 따라 다수의 캐릭터들이 등장하는 장면을 쉽게 접할 수 있다. 가상 환경에서 군중의 행동을 효율적으로 처리하는 기술에 관련해서 군중 장면 처리 및 군중 행동 시스템의 구현에 관한 연구는 있었으나, 자연스러운 군중 행동 시뮬레이터를 개발하는 연구는 아직 미흡한 편이다. 본 논문에서는 가상 해저환경에 존재하는 다수의 물고기들의 행동유형을 스마트하게 표현하여 시간과 비용이 많이 소요되는 단점을 보완하며 fish 군중행동 유형을 자동화하면서 사실적이면서 효율적인 가상 해저 환경 콘텐츠 제작을 구현하기 위한 fish 군중행동 시뮬레이터를 개발한다.

• 로봇학회논문지
• /
• 제14권2호
• /
• pp.139-149
• /
• 2019

In this paper, we present auto-annotation tool and synthetic dataset using 3D CAD model for deep learning based object detection. To be used as training data for deep learning methods, class, segmentation, bounding-box, contour, and pose annotations of the object are needed. We propose an automated annotation tool and synthetic image generation. Our resulting synthetic dataset reflects occlusion between objects and applicable for both underwater and in-air environments. To verify our synthetic dataset, we use MASK R-CNN as a state-of-the-art method among object detection model using deep learning. For experiment, we make the experimental environment reflecting the actual underwater environment. We show that object detection model trained via our dataset show significantly accurate results and robustness for the underwater environment. Lastly, we verify that our synthetic dataset is suitable for deep learning model for the underwater environments.