单一数据采集方式难以全面捕捉船舶结构的复杂细节，本文提出基于多源数据融合的船舶结构三维网格模型生成方法。在同一个无人机上搭载激光雷达装置、正摄像机，分别采集船舶激光点云数据、影像数据，将2种船舶结构数据坐标投影变换，融合多源数据，融合后数据作为船舶结构三维网格建模的数据样本，通过求解泊松方程，推断出船舶结构实体的近似指示函数，利用该函数构建等值面，连接各个等值面，生成三维网格模型。实验结果表明，本文方法能够采用多源数据融合的方式，构建与实际船舶结构数据高度拟合的三维网格模型。
It is difficult to capture the complex details of ship structure comprehensively by a single data acquisition method. Therefore, this paper proposes a generation method of three-dimensional grid model of ship structure based on multi-source data fusion. A laser radar device and a camera are mounted on the same UAV, and the laser point cloud data and image data of the ship are collected respectively. The coordinates of the two kinds of ship structure data are projected and transformed, and multi-source data are fused. The fused data are used as data samples for 3D grid modeling of the ship structure. By solving Poisson equation, the approximate indicator function of the ship structure entity is deduced, and the isosurface is constructed by using this function, and the three-dimensional grid model is generated. The experimental results show that the research method can use multi-source data fusion to construct a three-dimensional grid model that is highly fitted to the actual ship structure data.
2025,47(3): 167-171 收稿日期：2024-8-12
DOI：10.3404/j.issn.1672-7649.2025.03.028
分类号：TP391
基金项目：2024辽宁省属本科高校基本科研业务费专项资金资助项目（LJ112410144044）
作者简介：操宛霖(1993-),女,博士,讲师,研究方向为智能技术与空间设计
参考文献：
[1] 苏博越, 翟树成, 白亚强, 等. 尾鳍摆动推进水动力与流动涡结构特征分析[J]. 船舶力学, 2024, 28(2): 220?228.
SU B Y, ZAI S C, BAI Y Q, et al. Numerical study on the vortex structure and hydrodynamic characteristics for oscillating caudal fins[J]. Journal of Ship Mechanics, 2024, 28(2): 220?228.
[2] CHOI L, YOUN D, CHOI M, et al. Modular production of small ship models using 3D printing for model tests[J]. Ocean engineering, 2024, 302(6): 1.1?1.12.
[3] 太志伟, 张兴龙, 尹晓龙, 等. 三维船舶模型边界表示转构造表示方法[J]. 计算机辅助设计与图形学学报, 2023, 35(12): 1851?1862.
TAI Z W, ZHANG X L, YIN X L,et al. A method for transforming B-Rep of 3D ship models into CSG[J]. Journal of Computer-Aided Design & Computer Graphics, 2023, 35(12): 1851?1862.
[4] 徐思豪, 陈熠画, 彭亚康, 等. 基于知识工程的面向船体结构总体振动的计算网格生成方法[J]. 船海工程, 2024, 53(1): 1?6.
XU S H, CHEN Y H, PENG Y K, et al. A method of generating ship structure vibration model based on knowledge based engineering[J]. Ship & Ocean Engineering, 2024, 53(1): 1?6.
[5] 王晓琦, 赵旸, 张键, 等. 基于深度学习的船体三维模型自动生成方法[J]. 兵工学报, 2022, 43(z2): 115?119.
WANG X Q, ZHAO Y, ZHANG J. 3D ship model generation algorithm based on deep learning[J]. Acta Armamentarii, 2022, 43(z2): 115?119.
[6] 李松龙, 柳晨光, 初秀民, 等. 船舶编队过闸航行三维实时仿真[J]. 中国航海, 2022, 45(3): 129?136.
LI S L, LIU C G, CHU X M, et al. Real time 3D simulation of lockage of ship formation[J]. Navigatin of China, 2022, 45(3): 129?136.
[7] 李凯, 于洪亮, 徐轶群, 等. 基于光学遥感影像的船舶目标识别[J]. 中国航海, 2022, 45(1): 95?100.
LI K, YU H L, XU Y Q, et al. Ship target recognition from optical remote sensing image[J]. Navigatin of China, 2022, 45(1): 95?100.
[8] 孙梦丹, 汪雪良, 吴国庆, 等. 基于实船结构监测数据的异常检测及处理方法[J]. 装备环境工程, 2023, 20(9): 152?159.
SUN M D, WANG X L, WU G Q, et al. Anomaly detection and processing method based on real ship structure monitoring data[J]. Equipment Environmental Engineering, 2023, 20(9): 152?159.
