• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1104-1105
• /
• 2023

조선업계에서 전문 인력 수급난으로 난항을 겪고 있다. 이는 선박의 검사에 차질을 빚었고 해양 오염과 선박사고와 같은 문제가 발생하고 있다. 이에 안전 검진 수행에 AI 이미지 인식 기반 진단 모델을 적용하여, 애플리케이션을 통해 비전문가도 품질 진단을 수행할 수 있도록 한다.

• Journal of Advanced Navigation Technology
• /
• v.23 no.5
• /
• pp.367-372
• /
• 2019

With the development of various IT technologies, data generated in the ship can be controlled through CAN communication, autonomous operation, and information provision in various situation. In addition, electronic navigation vessels with various functions have emerged, and navigation and communication equipment used in these vessels are mainly following the NMEA standard. Currently, NMEA-0183 is still mainly used, but more efficient multimedia transmission processing method is needed for multimedia transmission and USN equipment compatible using NMEA-2000 standard. Furthermore, Ethernet-based ship control is required. However, this paper proposes a multimedia transmission scheme to be smoothly linked with existing ship devices by utilizing CAN communication that can be easily used in the ship.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.3
• /
• pp.42-50
• /
• 2010

It is necessary to implementation of system contain intelligent decision making algorithm considering marine feature because existing vessel USN system is simply monitoring obtained data from vessel USN. In this paper, we designed inference system using case based reasoning method and implemented knowledge base that case for fire and demage of digital marine vessel. We used K-Nearest Neighbor algorithm for recommend best similar case and input 3.000 EA by case for fire and demage context case base. As a result, we obtained about 82.5% average accuracy for fire case and about 80.1% average accuracy for demage case. We implemented digital marine vessel monitoring system using inference result.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.7 no.3
• /
• pp.1-16
• /
• 2001

In view of the fact that marine casualties have more often occurred recently, there is a need for ship-handling simulator as a useful tool for maritime training, safety assessment and so on. Moreover various kinds of hull forms have appeared for the purpose of improving ship manoeuvrality. Therefore ship-handling simulator is in need of a database for various ships, and it can make diverse maneuvering simulations possible to apply respective mathematical model to ship-handling simulator. In this paper, we adopted twin-screw and twin-rudder ship and discussed mathematical model of maneuvering motions for her. It was discussed from the viewpoint of hull damping forces at low advance speed and interaction between hull, propeller and rudder. Using this model, maneuvering motion of twin-screw and twin-propeller ship was simulated numerically and her principal manoeuvrability was examined.

• Proceedings of KOSOMES biannual meeting
• /
• 2003.11a
• /
• pp.59-65
• /
• 2003

For safe passing the waterway crossing bridge without collision with bridge-piers under poor visibility circumstances, it is very important that the pier should be detected definitely as earlier as possible by radar, In this study, the required length of Projecting part of the bridge pier for definite radar recognition was obtained by theoretical and experimental analyses. By presenting the required values depending on the maximum vessel size and passing condition, it is expected possible to design the bridge pier protecting system appropriately suitable to traffic environment of the waterway.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.174-178
• /
• 1999

Recently, the computer vision has been applied to many automation fields. Especially, this paper presents a maritime traffic detection system using computer vision since the high level information can be obtained using obtained area information. The high level informations are obtained such as speed, queueing length, queueing time, ship size, and ship kind. To get ship speed, the two detection lines are set on the predetermined screen position. The speed is obtained the passing time and the predetermined distance between the first and second detection line on the screen. Also, queueing length and time are gotten using screen position of ship. Furthermore, the size and kind of ship are calculated using the ship database and camera calibration data. This developed system contributes to reduce the traffic accidents on the coast. Futhermore, the more information can be extracted using obtained area information.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.10a
• /
• pp.175-178
• /
• 2015

This paper presents a VR-simulated sailor training platform for emergency in order to prevent a human error that causes 60~80% of domestic/ abroad marine accidents. Through virtual reality technology, the proposed platform provides an interaction method for proficiency of procedures in emergency, and a crowd control method for controlling crowd agents in a virtual ship environment. The interaction method uses speech recognition and gesture recognition to enhance the immersiveness and efficiency of the training. The crowd control method provides natural simulations of crowd agents by applying a behavior model that reflects the social behavior model of human. To examine the efficiency of the proposed platform, a prototype whose virtual training scenario describes the outbreak of fire in a ship was implemented as a standalone system.

• Korean Journal of Remote Sensing
• /
• v.34 no.5
• /
• pp.801-810
• /
• 2018

Ship monitoring using satellite synthetic aperture radar (SAR) images consists of ship detection, ship discrimination, and ship classification. A large number of methods have been proposed to improve the detection and discrimination capabilities, while only a few studies exist for ship classification. Thus, many studies for the ship classification are needed to construct ship monitoring system having high performance. Note that constructing database (DB), which contains both SAR images and labels of various ships, is important for research on the ship classification. In the airborne SAR classification, many methods have been developed using moving and stationary target acquisition and recognition (MSTAR) DB. However, there has been no publicly available DB for research on the ship classification using satellite SAR images. Recently, Shanghai Key Laboratory has constructed OpenSARShip DB using both SAR images of various ships generated from Sentinel-1 satellite of European Space Agency (ESA) and automatic identification system (AIS) information. Thus, the applicability of OpenSARShip DB for ship classification should be investigated by using the concepts of airborne SAR classification which have shown high performances. In this study, ship classification using satellite SAR images are conducted by applying the concepts of airborne SAR classification to OpenSARShip DB, and then the applicability of OpenSARShip DB is investigated by analyzing the classification performances.

• Journal of Navigation and Port Research
• /
• v.42 no.1
• /
• pp.25-30
• /
• 2018

This study was carried out to analyze the risk attitude based on situation awareness of the Vessel Traffic Service Operator (VTSO) on the risk of collision between vessels during the monitoring of vessel traffic through the use of the VTS system. In general, when two vessels are in the close quarters situation, we analyzed the degree of risk of collision from the subjective viewpoint of the VTSOs through an administered survey. Chiefly, we analyzed the risk attitudes of each VTSO in the close quarters situation, by comparing it with the calculated value by the CoRi, which is the ship collision risk model from the VTSO's viewpoint. As a result, it was confirmed that more than 40% of the total VTSO was noted as being in a weak risk aversion type of category. Through a review of the results of analyzing the risk attitude of VTSO according to gender, age, VTS career, VTS center position, accident experience, and boarded career, it was found that there was a significant difference in the VTS career, VTS center position and accident experience. In addition, a regression model that is able to further explain the risk attitude of VTSO was derived as a factor that confirmed the significant difference and applied to CoRi to predict the collision risk according to the individual VTSO to be used as a fundamental information gathering tool for providing more accurate and safe VTS service at sea.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2014.06a
• /
• pp.232-234
• /
• 2014

현재 연안여객선의 여객과 화물의 승선 예매 및 발권시스템은 타 교통수단에 비교하여 매우 부족하며 여객이 느끼는 실질적인 서비스 수준도 상대적으로 미흡하다는 평가를 받고 있다. 해양수산부 등 관련 기관에서는 이를 개선하기 위해 승선권 무인취급시스템 등을 구축하고자 노력하고 있으나 아직 부족한 현실이다. 본 연구에서는 여객 및 화물 정보를 QR-Code 등을 통하여 인식한 후, 선박 자체관리 프로그램 및 Web상에서 연동되는 선박예매/발권시스템을 구축하였다. 시스템의 Database 정보에는 승선객의 프로파일 정보, 중간기착지 방문 정보, 여객의 최초승선지 및 하선 정보, 화물 적양하 기록 등이 포함된다.