인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
DBpia AI
AI 에이전트
AI 아이디어
AI 리더
AI 뷰어
Citeasy
크롬 서지관리 다운로드
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
학술저널
Full-text XML
오류 신고하기해당 페이지 내 제목·저자·목차·페이지정보가 잘못된 경우 알려주세요!
초록·키워드
Detecting deformations in ship hull structures is crucial for maritime safety and ship maintenance. Conventional deformation detection techniques tend to be costly, time-consuming, and often require complex equipment. This study proposes an efficient and accurate method for detecting ship hull deformations using a monocular camera. The method involves capturing images of the deformed hull surface, estimating depth through image analysis, and converting the estimated depth data into a point cloud.
The point cloud is then used to establish a reference plane from the projected points, and deviations and curvature relative to this plane are measured to identify deformed areas. The proposed technique demonstrates its validity by comparing the results with actual deformation regions. Despite relying on only a single image, the method shows high accuracy and the potential for detecting deformations across various ship hull types. The efficiency of deformation detection is further improved by image analysis techniques that calculate the curvature of the deformed hull. Furthermore, the method shows the potential to handle unlabeled data, providing a significant advantage over deep learning models that typically require large datasets, as it can function effectively with just one image.
The point cloud is then used to establish a reference plane from the projected points, and deviations and curvature relative to this plane are measured to identify deformed areas. The proposed technique demonstrates its validity by comparing the results with actual deformation regions. Despite relying on only a single image, the method shows high accuracy and the potential for detecting deformations across various ship hull types. The efficiency of deformation detection is further improved by image analysis techniques that calculate the curvature of the deformed hull. Furthermore, the method shows the potential to handle unlabeled data, providing a significant advantage over deep learning models that typically require large datasets, as it can function effectively with just one image.
본문·목차
인공지능 문자 인식 모델을 통해 추출된 텍스트로, 일부 오타나 오류가 포함될 수 있으나 지속적으로 개선 중입니다.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
최근 본 자료 전체보기
UCI(KEPA) : I410-151-25-02-092724867
