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.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2024.6
- 수록면
- 85 - 93 (9page)
- DOI
- 10.7315/CDE.2024.085
이용수
초록· 키워드
오류제보하기
This paper presents the deep learning based point classification method for 3D plates. When a 3D point set or point cloud from curved plate is given as the input, the proposed method first computes various geometric information to provide clues for detecting boundary and hole boundary points. In this paper, three geometric information values are computed, which are the biggest angle gap, the distance between a query point and centroid of its neighborhood, and the distance between a query point and centroid of the whole point set. After geometric information computation is completed, the proposed method applies the deep neural network (Point-Net) to classify input points. In order to efficiently train the network, synthetic plates are created with various shapes and grid sizes. The paper performs the experiments to test effects of the geometric information, and shows that using the geometric information indeed helps the neural network to understand topological information of the input pointset, which actually improves the performance of point classification.
목차
ABSTRACT
1. 서론
2. 알고리즘
3. 실험 결과
4. 결론
References
참고문헌 (21)
참고문헌 신청
Jarng, S.S., Yang, H.J. and Lee, J.H., 2005, Finite Element Mesh Generation from 3D Laser Scanned Data, Korean Journal of Computational Design and Engineering, 10(1), pp.70-75.
Jang, T.H., Baek, S.Y. and Lee, K.W., 2009, Synthesis of Human Body Shape for Given Body Sizes using 3D Body Scan Data, Korean Journal of Computational Design and Engineering, 14(6), pp.364-373.
Hwang, H.J., Mun, D.H. and Hwang, J.S., 2010, Construction of 3D Geometric Surface Model from Laminated CT Images for the Pubis, Korean Journal of Computational Design and Engineering, 15(3), pp.234-242.
Schönberger, J.L. and Frahm, J.M., 2016, Structure-from-motion Revisited, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp.4104-4113, https://doi.org/10.1109/CVPR.2016.445.
Lee, I.D., Lee, I. and Han, S., 2021, 3D Reconstruction of As-built Model of Plant Piping System from Point Clouds and Port Information, Journal of Computational Design and Engineering, 8(1), pp.195-209, https://doi.org/10.1093/jcde/qwaa072.
Jang, T.H., Baek, S.Y. and Lee, K.W., 2009, Synthesis of Human Body Shape for Given Body Sizes using 3D Body Scan Data, Korean Journal of Computational Design and Engineering, 14(6), pp.364-373.
Hwang, H.J., Mun, D.H. and Hwang, J.S., 2010, Construction of 3D Geometric Surface Model from Laminated CT Images for the Pubis, Korean Journal of Computational Design and Engineering, 15(3), pp.234-242.
Schönberger, J.L. and Frahm, J.M., 2016, Structure-from-motion Revisited, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp.4104-4113, https://doi.org/10.1109/CVPR.2016.445.
Lee, I.D., Lee, I. and Han, S., 2021, 3D Reconstruction of As-built Model of Plant Piping System from Point Clouds and Port Information, Journal of Computational Design and Engineering, 8(1), pp.195-209, https://doi.org/10.1093/jcde/qwaa072.
이 논문과 함께 이용한 논문
주조 공정에서 제어 로직과 온도 데이터를 활용한 CNN Autoencoder 기반 공정 이상 진단
오소향
,
양정삼
한국CDE학회 논문집
2024
.09
CNN 기반 선박 형광 도막 두께 측정
하제민
,
김근완
,
이경태
외 2명
한국CDE학회 논문집
2022
.12
기계학습을 이용한 3D CAD 모델 형상과 경계조건의 유형 식별
김준성
,
박형준
한국CDE학회 논문집
2022
.09
자율 운항 선박을 위한 딥 러닝 기반 선박 이미지 분류 방법
남권우
,
노명일
,
이혜원
외 1명
한국CDE학회 논문집
2021
.06
다양한 딥러닝 알고리즘과 활용
김지원
,
표현아
,
하정우
외 2명
정보과학회지
2015
.08
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-151-24-02-089809767