An investigation of geometric feature recognition in 3D ship data
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The intelligent recognition of ship geometric features is a prerequisite for enabling computers to automatically generate and deform ship hull surfaces according to requirements, thereby replacing the work of human designers to improve design efficiency. This paper aims to research the recognition of geometric features in threedimensional ship data using PointNet. To achieve this goal, we first construct two ship point cloud datasets suitable for global feature classification and feature part segmentation of three-dimensional hulls. Subsequently, we conducted recognition capability testing to determine the optimal hyperparameters for identifying ship feature networks. Finally, we employ ship models with non-standard positions to implement data augmentation, enhancing the network’s robustness in recognizing the initial positions of ships and achieving rapid cognition of three-dimensional ship geometric features. The findings of this research will provide technical support for ship design based on artificial intelligence technology.
Abstract
The intelligent recognition of ship geometric features is a prerequisite for enabling computers to automatically generate and deform ship hull surfaces according to requirements, thereby replacing the work of human designers to improve design efficiency. This paper aims to research the recognition of geometric features in threedimensional ship data using PointNet. To achieve this goal, we first construct two ship point cloud datasets suitable for global feature classification and feature part segmentation of three-dimensional hulls. Subsequently, we conducted recognition capability testing to determine the optimal hyperparameters for identifying ship feature networks. Finally, we employ ship models with non-standard positions to implement data augmentation, enhancing the network’s robustness in recognizing the initial positions of ships and achieving rapid cognition of three-dimensional ship geometric features. The findings of this research will provide technical support for ship design based on artificial intelligence technology.
참고문헌 (38)
- Campana, E. F., "Shape optimization in ship hydrodynamics using computational fluid dynamics", Comput. Methods Appl. Mech. Eng, 196(1–3), pp.634~651 (2006)
- Chen, X., "Individual tree crown segmentation directly from UAV-borne LiDAR data using the PointNet of deep learning", Forests, 12(2), pp.131~ (2021)
- Du, L., "Ship hull Offset feature recognition functionality exploration based on convolutional neural networks", Paper Presented at: the 32nd International Ocean and Polar Engineering Conference (2022)
- He, K., "Deep residual learning for image recognition", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770~778 (2016)
- Hu, Q., "Randla-net: efficient semantic segmentation of large-scale point clouds", Proceedings of the IEEE, 2020, 11108~11117
- Huo, S., "A Broadly Applicable Coarse Alignment Framework for the Point Cloud of Hull Blocks", ~
- Khan, S., "ShipHullGAN : a generic parametric modeller for ship hull design using deep convolutional generative model", Comput. Methods Appl. Mech. Eng, 411, pp.116051~ (2023)
- Kim, D., "CNN-based fire detection method on autonomous ships using composite channels composed of RGB and IR data", Int. J. Nav. Archit. Ocean Eng, 14, pp.100489~ (2022)
- Kim, J. H., "Prediction of the superiority of the hydrodynamic performance of hull forms using deep learning", Int. J. Nav. Archit. Ocean Eng, 14, pp.100490~ (2022)
- Ko, K. H., "A survey : application of geometric modeling techniques to ship modeling and design", Int. J. Nav. Archit. Ocean Eng, 2(4), pp.177~184 (2010)
- Krizhevsky, A., "Imagenet classification with deep convolutional neural networks", Adv. Neural Inf. Process. Syst, pp.25~ (2012)
- Lecun, Y., "Gradient-based learning applied to document recognition", Proc. IEEE, 86(11), pp.2278~2324 (1998)
- Lee, D. K., "A case study for 3D scanning-based quantitative quality control during key stages of composite small craft production", Int. J. Nav. Archit. Ocean Eng, 15, pp.100534~ (2023)
- Li, S. Z., "Multiobjective optimization for ship hull form design using SBD technique", Comput. Model. Eng. Sci, 92(2), pp.123~149 (2013)
- Li, S., "Application of mesh deformation and adaptive method in hullform design optimization", J. Mar. Sci. Technol, pp.1~10 (2022)
- Liu, H., "Pd-gan: probabilistic diverse gan for image inpainting", Proceedings of the IEEE, 2021, 9371~9381
- Liu, Y., "FCP-net : a featurecompression-pyramid network guided by game-theoretic interactions for medical image segmentation", IEEE Trans. Med. Imag, 41(6), pp.1482~1496 (2022)
- McCulloch, Warren S., "A logical calculus of the ideas immanent in nervous activity", Bull. Math. Biophys, 5(4), pp.115~133 (1943)
- Qi, R. C., "PointNet : deep learning on point sets for 3D classification and segmentation", CoRR (2016)
- Qi, R Charle, "PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric space" (2017)
- Rosu, R. A., "Latticenet : fast spatio-temporal point cloud segmentation using permutohedral lattices", Aut. Robots, 46(1), pp.45~60 (2022)
- Salomons, O. W., "Review of research in feature-based design", J. Manuf. Syst, 12(2), pp.113~132 (1993)
- Sarmad, M., "Rl-gan-net: a reinforcement learning agent controlled gan network for real-time point cloud shape completion", Proceedings of the IEEE, 2019, 5898~5907
- Shelhamer, Evan, "Fully convolutional networks for semantic segmentation", IEEE Trans. Pattern Anal. Mach. Intell, 39(4), pp.640~651 (2017)
- Soil´an Rodríguez, M., "Pointnet for the automatic classification of aerial point clouds", ISPRS Ann. Photogr. Rem. Sens. Spatial Inform. Sci, 4, pp.445~452 (2019)
- Song, J., "Unorganized point classification for robust NURBS surface reconstruction using a point-based neural network", Journal of Computational Design and Engineering, 8(1), pp.392~408 (2021)
- Su, Hang, "Multi-view Convolutional Neural Networks for 3D Shape Recognition" (2015)
- Szegedy, C., "Going deeper with convolutions", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1~9 (2015)
- Tchapmi, Lyne, "SEGCloud: Semantic Segmentation of 3D Point Clouds", ~ (2017)
- Wang, J., "Research of fast point cloud registration method in construction error analysis of hull blocks", Int. J. Nav. Archit. Ocean Eng, 12, pp.605~616 (2020)
- Yan, Yan, "SECOND: sparsely embedded convolutional detection", Sensors, 18(10), pp.3337~ (2018)
- Yin, Zhou, "VoxelNet: End-To-End Learning for Point Cloud Based 3D Object Detection" (2017)
- Zhang, J., "Why Adam Beats Sgd for Attention Models", ~ (2019)
- Zhang, W., "Application Research of ship overload identification algorithm based on lidar point cloud", 2022 2nd International Conference on Electrical Engineering and Mechatronics Technology (ICEEMT), pp.377~381 (2022), IEEE
- Zhao, J., "A ship trajectory prediction method based on GAT and LSTM", Ocean Eng, 289, pp.116159~ (2023)
- Zheng, C., "Pluralistic image completion", Proceedings of the IEEE, 2019, 1438~1447