• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.40-41
• /
• 2023

This paper introduces the design of detection, recognition, and tracking algorithms for VTS radar image-based objects. The detection of objects in radar images utilizes artificial intelligence technology to determine the presence or absence of objects, and can classify the type of object using AI technology. Tracking involves the continuous tracking of detected objects over time, including technology to prevent confusion in the movement path. In particular, for land-based radar, there are unnecessary areas for detection depending on the terrain, so the function of detecting and recognizing vessels within the region of interest (ROI) set in the radar image is included. In addition, the extracted coordinate information is designed to enable various applications and interpretations by calculating speed, direction, etc.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.177-188
• /
• 2021

In South Korea, with the advancement of the 'Port' project, the regeneration industry adapted to the modern economic development has been promoted, leading to construction around the port was also redefined. Therefore, through regeneration, the problem of image construction of buildings around the port has been re-examined, in which color is an important content of image construction. In this study, the exterior walls of abandoned factory buildings in the port area of Bongnaedong, Pusan were selected as the color research object and evaluated according to the characteristics of the regenerated factory buildings combined with the building color function. Technically, KSCP color analysis system is used for color analysis. In this way, the color plan for the exterior walls of the factory buildings is proposed to visually enhance the image of abandoned factory buildings and attract more attention, thus driving the regional economic development. The results of this study show that in order to adapt to the regional, industrial and commercial characteristics of the regenerated port space, the color hue, lightness, chroma and use area of the building can be changed to enhance the aesthetic value and enhance the inductivity and security.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2007.12a
• /
• pp.136-137
• /
• 2007

This study was to analyze the visual preference of the port landscapes for North port in Busan. Preference related variables came from Semantic Differential(SD) method and then were conducted by the factor analysis. Multiple regression was done for the relationship between the preference and factors. The result found 4 factors, including dynamics, stability, pleasantness and healthiness. Much importance was placed on dynamics among them. Therefore, building port landscapes and their image attracting viewers should consider dynamics in terms of port landscape plan and user attraction development for visual quality management.

• Journal of Navigation and Port Research
• /
• v.32 no.3
• /
• pp.265-269
• /
• 2008

This study was to analyze the visual preference of the port landscapes for North port in Busan. Preference related variables came from Semantic Differential(SD) method and then were conducted by the factor analysis. Multiple regression was done for the relationship between the preference and factors. The result found 4 factors, including dynamics, stability, pleasantness and healthiness. Much importance was placed on dynamics among them. Therefore, building port landscapes and their image attracting viewers should consider dynamics in terms of port landscape plan and user attraction development for visual quality management.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.69-72
• /
• 2024

모델 역추론 공격은 공격 대상 네트워크를 훈련하기 위해 사용되는 훈련 데이터셋 중 개인 데이터셋을 공개 데이터셋을 사용하여 개인 훈련 데이터셋을 복원하는 것이다. 모델 역추론 방법 중 적대적 생성 신경망을 사용하여 모델 역추론 공격을 하는 과거의 논문들은 딥러닝 모델 전체의 역추론에만 초점을 맞추기 때문에, 이를 통해 얻은 원본 이미지의 개인 데이터 정보는 제한적이다. 따라서, 본 연구는 대상 모델의 중간 출력을 사용하여 개인 데이터에 대한 더 품질 높은 정보를 얻는데 초점을 맞춘다. 본 논문에서는 적대적 생성 신경망 모델이 원본 이미지를 생성하기 위해 사용되는 계층별 역추론 공격 방법을 소개한다. MNIST 데이터셋으로 훈련된 적대적 생성 신경망 모델을 사용하여, 원본 이미지가 대상 모델의 계층을 통과하면서 얻은 중간 계층의 출력 데이터를 기반으로 원본 이미지를 재구성하고자 한다. GMI 의 공격 방식을 참고하여 공격 모델의 손실 함수를 구성한다. 손실 함수는 사전 손실 및 정체성 손실항을 포함하며, 역전파를 통해서 원본 이미지와 가장 유사하게 복원할 수 있는 표현 벡터 Z 를 찾는다. 원본 이미지와 공격 이미지 사이의 유사성을 분류 라벨의 정확도, SSIM, PSNR 값이라는 세 가지 지표를 사용하여 평가한다. 공격이 이루어지는 계층에서 복원한 이미지와 원본 이미지를 세 가지 지표를 가지고 평가한다. 실험 결과, 공격 이미지가 원본 이미지의 대상 분류 라벨을 정확하게 가지며 원본 이미지의 필체를 유사하게 복원하였음을 보여준다. 평가 지표 또한 원본 이미지와 유사하다는 것을 나타낸다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.323-324
• /
• 2022

복잡한 항만해역에서 자율운항선박 입출항 지원을 위해서는 항내에서 통항하는 선박에 대한 지속적인 인식이 필요하며, 이를 위해 선박자동식별시스템(AIS)에서 송출된 정보를 기반으로 선박의 운동정보(위치/침로/속도), 식별번호 및 크기 정보를 확인한다. 하지만, AIS 탑재 의무가 있는 선박에 대한 정보만 취득이 가능하기 때문에, 보조적으로 육상레이더를 활용하여 AIS 정보로부터 식별이 안되는 선박을 인식할 수 있는 기술이 필요하다. 본 연구에서는 자율운항선박 입출항 지원을 위해 레이더 이미지를 활용하여 선박의 운동정보와 형상정보를 동시에 추정할 수 있는 알고리즘을 설계하였다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.11a
• /
• pp.77-79
• /
• 2023

국내 대표 해양도시인 부산시는 도시의 이미지를 향상시키고 경쟁력을 갖추기 위해 북항재개발지역과 원도심지역을 연계한 복합형 재생사업을 추진하고 있다. 부산남항은 북항과 원도심지역에 맞닿아있지만 고유의 특성이 고려되지 못하고 복합형 재생사업에 종속된 개발 압력을 받아왔다. 최근 해양관광벨트 형성에 있어 부산남항의 입지적 중요성과 북항·원도심지역과의 연계 필요성이 대두되며 부산남항을 대상으로 다양한 개발계획이 수립되고 있다. 항만재개발사업의 경우 대규모 SOC사업으로 추진과정에서 이해관계자 간의 갈등, 재정 문제 등의 여러 문제가 야기되는데 이러한 문제를 해결하지 못하면 사업이 표류 될 가능성이 크다. 따라서 본 연구는 부산남항 재창조를 위해 필수적인 항만재개발사업의 원활한 진행을 위한 추진전략과 민간참여방안을 제시하였다.

• Journal of Korea Port Economic Association
• /
• v.25 no.2
• /
• pp.259-276
• /
• 2009

The study herein has focused on offering foundation infrastructure in order for seamen who arrive at Korean ports to use internet service smoothly in waiting time and free time. It also concentrated on how to build communication infrastructure for efficient operations when improving existing ports and developing new ports. For this, it has grasped the tendency of researches concerning the existing port communication and has also investigated the status and problems of communication infrastructure being used currently in ports. So it has suggested several realistic development methods based on mesh network and has reviewed them in terms of the stability, economic feasibility and efficiency. Additionally, this research offers the results of the performance test conducted on major equipment in market by the suggested methods. This research can be a good guideline in building wireless communication systems of ports and is expected to contribute to creating traffic volume by improving the image of ports.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.323-324
• /
• 2022

This paper explains the comparison results of surface current measurement using X-band Radar image through analysis. Measurements were carried out from February 2022 using the X-band Radar for marin ships installed at Sokcho Beach. Based on the Korea Hydrographic and Oceanographic Agency ocean observation buoys, the accuracy of surface current(current speed) measurement was verified through comparison and analysis of measurement data.

• Journal of Navigation and Port Research
• /
• v.35 no.5
• /
• pp.423-428
• /
• 2011

The more the need for coastal leisure and sports and the expansion of marina, the more the need for the studies about marina. But little research has been done from the point of coastal tourism. The purpose of this study is to recognize marina as a kind of tourist attraction and analyze the effect of marina landscape design to images. The findings of results suggested that perceived images were significant to the functionality of landscape design, however, emotional images were partly significant to the symbolicity of landscape design. This study will contribute to establish the landscape regulations about marina in the central and local government.