Please wait a minute...
浙江大学学报(理学版)  2022, Vol. 49 Issue (1): 19-26    DOI: 10.3785/j.issn.1008-9497.2022.01.003
图形模拟与目标跟踪     
三维鱼体参数化建模
胡海涛1,赵银君1,石敏1(),赵国亮1,朱登明2
1.华北电力大学 控制与计算机工程学院,北京 102206
2.中国科学院计算技术研究所 前瞻研究实验室,北京 100190
Parametric modeling of 3D fish body
Haitao HU1,Yinjun ZHAO1,Min SHI1(),Guoliang ZHAO1,Dengming ZHU2
1.School of Control and Computer Engineering,North China Electric Power University,Beijing 102206,China
2.Virtual Reality Laboratory,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China
 全文: PDF(1843 KB)   HTML( 7 )
摘要:

因水下环境复杂,鱼类三维模型获取非常困难,基于三维鱼类数据驱动的很多自动化研究工作无法开展。为此,提出一种三维鱼体参数化建模方法。首先,用专业建模师构建的标准鱼体模板注册扫描仪采集三维鱼体数据,构建拓扑结构一致的三维鱼体网格数据集;其次,用主成分分析法对数据集中的三维鱼体网格模型进行建模分析,建立鱼体的参数化表示模型;最后,采集草鱼数据进行相关实验。实验结果表明,注册得到的三维鱼体模型与真实扫描鱼体模型顶点之间的平均均方根误差仅为0.691 3 mm,在可接受范围。通过改变三维鱼体参数化表示模型中的权参数,快速生成了大量三维鱼体数据,从而解决了三维鱼体数据获取困难的问题。

关键词: 三维鱼体网格注册主成分分析参数化建模    
Abstract:

The complex underwater environment makes it difficult to obtain 3D fish models, leading to the fact that many automated research work based on 3D fish data cannot be carried out. This paper proposes a 3D fish body parametric modeling method. Firstly, we use the standard fish body template constructed by a professional modeler to register the 3D fish body data collected by the scanner, and construct a 3D fish body mesh dataset with consistent topological structure; Secondly, we apply the principal component analysis method to model and analyze the 3D fish body mesh model in the dataset establishing a parameterized representation model of the fish body. We take the collected grass carp data to verify the effectiveness of the above approach. The experimental results show that the root mean square error between the vertices of the registered 3D fish model and the real scanned fish model is only 0.691 3 mm. By changing the weight parameters of the constructed 3D fish body parameterized model, a large amount of 3D fish body data can be quickly generated.

Key words: 3D fish body    grid registration    principal component analysis    parametric modeling
收稿日期: 2021-06-11 出版日期: 2022-01-18
CLC:  TP 319  
基金资助: 中国科学院科研仪器设备研制项目(YJKYYQ20190055);国家自然科学基金资助项目(61972379)
通讯作者: 石敏     E-mail: shi_min@ncepu.edu.cn
作者简介: 胡海涛(1973—),ORCID:https://orcid.org/0000-0002-8561-6634,男,博士,副教授,主要从事软件体系结构、面向服务计算、软件集成等研究.
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
胡海涛
赵银君
石敏
赵国亮
朱登明

引用本文:

胡海涛,赵银君,石敏,赵国亮,朱登明. 三维鱼体参数化建模[J]. 浙江大学学报(理学版), 2022, 49(1): 19-26.

Haitao HU,Yinjun ZHAO,Min SHI,Guoliang ZHAO,Dengming ZHU. Parametric modeling of 3D fish body. Journal of Zhejiang University (Science Edition), 2022, 49(1): 19-26.

链接本文:

https://www.zjujournals.com/sci/CN/10.3785/j.issn.1008-9497.2022.01.003        https://www.zjujournals.com/sci/CN/Y2022/V49/I1/19

图1  三维鱼体参数化建模方法
图2  三维鱼体标准模板构建
图3  非刚性ICP算法思想
图4  标准鱼体模板
图5  草鱼扫描数据采集
图6  刚性注册实验结果
图7  非刚性注册实验结果
扫描鱼序号均方根误差/mm配准时间/s
平均0.691 345.61
Fish00010.823 840.13
Fish00020.689 147.85
Fish00030.668 143.83
Fish00040.775 847.66
Fish00050.602 242.99
Fish00060.545 445.60
Fish00070.434 338.89
Fish00080.653 545.39
Fish00090.803 548.38
Fish00100.835 445.26
Fish00110.773 355.72
表1  鱼体非刚性注册均方根误差及配准时间
图8  三维鱼体平均体型
图9  鱼体定量分析示意
图 10  三维鱼体模型随权参数w1的变化(a) w1=0.851 (b) w1=1.000 (c) w1=1.135
权参数w1体长/mm体高/mm体宽/mm
0.851358.99154.49107.80
1.000424.72171.15125.54
1.135485.23194.97141.30
表2  权参数w1对鱼体体型的影响
权参数体长/mm体高/mm体宽/mm

w2

0.000423.55170.90120.63
1.000424.72171.15125.54
3.309428.05171.80136.91

w3

-0.216426.40173.76128.52
1.000424.72171.15125.54
2.950425.57167.54122.23

w4

-1.942425.71172.53119.10
1.000424.72171.15125.54
2.086424.37170.52127.84
表3  权参数w2,w3,w4对鱼体体型的影响
1 BERTALANFFY L VON. A quantitative theory of organic growth(inquiries on growth laws II)[J]. Human Biology, 1938, 10(2):181-213.
2 SIMMONDS E J, MACLENNAN D N. Fisheries Acoustics, Theory and Practices-Fish and Fisheries Series[M]. 2nd ed. Oxford: Blackwell Publishing, 2005:437.
3 MONTERO D, IZQUIERDO M S, TORT L, et al. High stocking density produces crowding stress altering some physiological and biochemical parameters in gilthead seabream, Sparus aurata, juveniles[J]. Fish Physiology and Biochemistry, 1999, 20(1): 53-60. DOI:10.1023/A:1007719928905
doi: 10.1023/A:1007719928905
4 MASSOT-CAMPOS M, OLIVER-CODINA G. Evaluation of a laser based structured light system for 3D reconstruction of underwater environments[C]// 5th Martech International Workshop on Marine Technology. Girona: SARTI, 2013. doi:10.1109/icsens.2014.6985208
doi: 10.1109/icsens.2014.6985208
5 BRUNO F, BIANCO G, MUZZUPAPPA M, et al. Experimentation of structured light and stereo vision for underwater 3D reconstruction[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(4): 508-518. DOI:10.1016/j.isprsjprs. 2011. 02.009
doi: 10.1016/j.isprsjprs. 2011. 02.009
6 YAU T H Y. Underwater Camera Calibration and 3D Reconstruction[D]. Edmonton: University of Alberta, 2014: 524-531. DOI:10.7939/R3ZC7S30V
doi: 10.7939/R3ZC7S30V
7 CHEN L Y. Surface reconstruction based on the 3D laser scanner[J]. Applied Mechanics and Materials, 2012,215/216:656-659. DOI:10.4028/www.scientific. net/amm.215-216.656
doi: 10.4028/www.scientific. net/amm.215-216.656
8 LI X S, QIN K Y, YAO P, et al. 3D surface reconstruction based on binocular vision[C]// 2014 IEEE International Conference on Mechatronics and Automation. Piscataway: IEEE, 2014: 1861-1865. DOI:10.1109/ICMA.2014.6885985
doi: 10.1109/ICMA.2014.6885985
9 ALLEN B, CURLESS B, POPOVIC Z. The space of human body shapes: Reconstruction and parameterization from range scans[J]. ACM Transactions on Graphics, 2003, 22(3): 587-594. DOI:10.1145/882262.882311
doi: 10.1145/882262.882311
10 ANGUELOV D, SRINIVASAN P, KOLLER D, et al. SCAPE: Shape completion and animation of people[J]. ACM Transactions on Graphics, 2005, 24(3): 408-416. DOI:10.1145/1073204.1073207
doi: 10.1145/1073204.1073207
11 LOPER M, MAHMOOD N, ROMERO J, et al. SMPL: A skinned multi-person linear model[J]. ACM Transactions on Graphics, 2015, 34(6):1-16: DOI:10.1145/2816795.2818013
doi: 10.1145/2816795.2818013
12 OSMAN A A A, BOLKART T, BLACK M J. STAR: Sparse trained articulated human body regressor[C]// Proceedings of the European Conference on Computer Vision. Cham: Springer, 2020: 598-613. DOI:10.1007/978-3-030-58539-6_36
doi: 10.1007/978-3-030-58539-6_36
13 BESL P J, MCKAY H D. A method for registration of 3D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 239-256. DOI:10.1109/34.121791
doi: 10.1109/34.121791
14 AMBERG B, ROMDHANI S, VETTER T. Optimal step nonrigid ICP algorithms for surface registration[C]// IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2007: 1-8. DOI:10.1109/CVPR.2007.383165
doi: 10.1109/CVPR.2007.383165
15 LI K, YANG J Y, LAI Y K, et al. Robust non-rigid registration with reweighted position and transformation sparsity[J]. IEEE Transactions on Visualization and Computer Graphics, 2019, 25(6):2255-2269. DOI:10.1109/TVCG. 2018. 2832136
doi: 10.1109/TVCG. 2018. 2832136
16 YAO Y X, DENG B L, XU W W, et al. Quasi-Newton solver for robust non-rigid registration[C]// IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 7597-7606. DOI:10.1109/CVPR42600.2020.00762
doi: 10.1109/CVPR42600.2020.00762
17 TU X Y, TERZOPOULOS D. Artificial fishes: Physics, locomotion, perception, behavior[C]// Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques. New York: Association for Computing Machinery, 1994: 43-50. DOI:10.1145/192161.192170
doi: 10.1145/192161.192170
18 ANDERSON J M, CHHABRA N K. Maneuvering and stability performance of a robotic tuna[J]. Integrative & Comparative Biology, 2002, 42(1):118-126. doi:10.1093/icb/42.1.118
doi: 10.1093/icb/42.1.118
19 BARRETT D S, TRIANTAFYLLOU M S, YUE D K P, et al. Drag reduction in fish-like locomotion[J]. Journal of Fluid Mechanics, 1999, 392: 183-212. DOI:10.1017/S0022112099005455
doi: 10.1017/S0022112099005455
20 MARCHESE A D, ONAL C D, RUS D. Autonomous soft robotic fish capable of escape maneuvers using fluidic elastomer actuators[J]. Soft Robotics, 2014, 1(1): 75-87. DOI:10.1089/soro. 2013.0009
doi: 10.1089/soro. 2013.0009
[1] 王钰帆,白强,孙虎. 2000—2020年汾河流域生态脆弱性时空演变与驱动因素[J]. 浙江大学学报(理学版), 2023, 50(5): 607-618.
[2] 陈珍慧, 鲁益飞, 胡江琴, 张漪, 金孝锋. 中国特有植物诸葛菜属(十字花科)的分类研究[J]. 浙江大学学报(理学版), 2017, 44(2): 201-205.
[3] 秦中伏, 雷小龙, 翟东, 金灵志. 基于SVM和LS-SVM的住宅工程造价预测研究[J]. 浙江大学学报(理学版), 2016, 43(3): 357-363.