基于深度学习的船体三维模型自动生成方法

doi:10.12382/bgxb.2022.B011

兵工学报 ›› 2022, Vol. 43 ›› Issue (S2): 115-119.doi: 10.12382/bgxb.2022.B011

基于深度学习的船体三维模型自动生成方法

王晓琦¹，赵旸¹，张键¹，王硕²

(1.中国船舶集团有限公司系统工程研究院，北京 100094；2.郑州大学电气与信息工程学院, 河南郑州 450001)

上线日期:2022-11-30
作者简介:王晓琦（1995—），女，工程师，硕士。E-mail：704310625@qq.com；
赵旸（1990—），男，高级工程师，硕士。E-mail：npu_zhaoyang@163.com；
张键（1979—），男，高级工程师，硕士。E-mail：otbc1@126.com；
王硕（1996—），男，硕士研究生。E-mail：1416878332@qq.com
基金资助:
中国船舶集团有限公司系统工程研究院科研项目(2021年)

3D Ship Model Generation Algorithm Based on Deep Learning

WANG Xiaoqi¹, ZHAO Yang¹, ZHANG Jian¹, WANG Shuo²

(1.CSSC Systems Engineering Research Institute, Beijing 100094, China；2.School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, Henan, China)

Online:2022-11-30

摘要/Abstract

摘要： 三维船体模型具有广泛的应用场景，但制作成本较高。提出一种基于深度学习的船体三维模型自动生成方法：通过卷积神经网络结构从一张二维平面图中提取角点；按照特定的规则将各角点组成线段，每一个线段表示一面墙体；将线段变换生成三维模型。制作500张二维船图用于模型训练，并制作30张二维船图用于测试。研究结果表明：新算法可以精确地检测输入图片的角点位置和种类，并生成清晰、美观、通用的三维模型，效果很好。

关键词: 船体三维模型, 深度学习, 船图, 卷积神经网络

Abstract: The 3D ship model has a wide range of application scenarios, but its production cost is high. We propose an automatic generation method of 3D ship model based on deep learning: corner points are extracted from a 2D plan with the convolution neural network structure; each corner point is formed into a line segment according to specific rules, and each line segment represents a wall; the line segments are transformed to generate the 3D model; 500 2D ship diagrams are made for model training, and 30 2D ship diagrams for testing. The results show that the new algorithm can accurately detect the corner positions and types of the input image, and generate clear, beautiful and universal 3D models, and the test results demonstrate that the proposed method is effective.

Key words: 3Dshipmodel, deeplearning, shipdiagrams, convolutionneuralnetwork

中图分类号:

U662.9

王晓琦，赵旸，张键，王硕. 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(S2): 115-119.

WANG Xiaoqi, ZHAO Yang, ZHANG Jian, WANG Shuo. 3D Ship Model Generation Algorithm Based on Deep Learning[J]. Acta Armamentarii, 2022, 43(S2): 115-119.

参考文献

［1］张丽.基于虚拟现实技术的船舶三维建模［J］.舰船科学技术,2022,44(9):40-43,56.
ZHANG L.Research on ship 3D modeling design based on virtual reality technology［J］. Ship Science and Technology,2022,44(9): 40-43,56.(in Chinese)
［2］陈波.船舶结构三维建模技术研究与软件开发［D］.大连:大连海事大学,2018.
CHEN B. Research and software development of ship structure 3D modeling technology［D］.Dalian: Dalian Maritime University,2018. (in Chinese)
[3］ RONNEBERGER O, PHILIPP F, THOMAS B.U-net: convolutional networks for biomedical image segmentation[C]∥Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention.Berlin,Germany:Springer, 2015:234-241.
［4］ SUN C,HSIAO C W,SUN M,et al. HorizonNet: learning room layout with 1D representation and panostretch data augmentation[C]∥Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, US:IEEE,2019.
[5］ YANG S T, WANG F E, PENG C H, et al. DuLa-Net: a dual-projection network for estimating room layouts from a single RGB panorama[C]∥Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach, CA, US:IEEE,2019.
[6］ ZOU C, COLBURM A, SHAN Q, et al. Layoutnet: reconstructing the 3d room layout from a single rgb image[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, US:IEEE,2018: 2051-2059.
[7］ ZHANG W D, ZHANG W,ZHANG Y D. GeoLayout: geometry driven room layout estimation based on depth maps of planes[C]∥Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer, 2020.
[8］ FURUKAWA Y, CURLESS B, SEITZ S M, et al. Reconstructing building interiors from images[C]∥Proceedings of the 2009 IEEE 12th International Conference on Computer Vision. Kyoto, Japan: IEEE, 2009: 80-87.
[9］ CABRAL R，FUSUTAKA Y. Piecewise planar and compact floorplan reconstruction from images[C]∥Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, US:IEEE, 2014.
[10］ HUANG J W,DAI A,GUIBAS L J, et al. 3Dlite: towards commodity 3D scanning for content creation[J]. SIGGRAPH Asia, 2017,36(6):1-14.
[11］ ZOLLHFER M, STOTKO P, GRLITZ A, et al. State of the art on 3D reconstruction with RGB-D cameras[J].Computer Graphics Forum,2018, 37(2): 625-652.
[12］ IKEHATA S, YANG H, FURUKAWA Y. Structured indoor modeling[C]∥Proceedings of the IEEE International Conference on Computer Vision.Santiago, Chile:IEEE, 2015: 1323-1331.
[13］ YAN F,NAN L, WONKA P. Block assembly for global registration of building scans[J]. ACM Transactions on Graphics, 2016,35(6):1-11.
[14］ XIAO J, FURUKAWA Y. Reconstructing the world's museums[J]. International Journal of Computer Vision, 2014, 110(3): 243-258.
[15］ VIDANAPATHIRANA M, WU Q R,FURUKAWA Y,et al. Plan2scene: converting floorplans to 3D scenes[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Nashville, TN, US:IEEE, 2021.
[16］ LIU C, WU J J,KOHLI P,et al. Raster-to-vector: revisiting floorplan transformation[C]∥Proceedings of the IEEE International Conference on Computer Vision.Venice, Italy:IEEE,2017.
[17］ RUBINSTEIN R. The cross-entropy method for combinatorial and continuous optimization[J]. Methodology and Computing in Applied Probability, 1999, 1(2): 127-190.

第43卷增刊22022 年11月
兵工学报ACTA ARMAMENTARII
Vol.43Suppl.2Nov. 2022

[1]	田大明, 苗圃. 融合模型求解与深度学习的可见光通信非线性均衡器[J]. 兵工学报, 2024, 45(2): 466-473.
[2]	张堃, 杜睿怡, 时昊天, 华帅. 基于Mogrifier-BiGRU的飞行器轨迹预测[J]. 兵工学报, 2024, 45(2): 373-384.
[3]	杨家铭, 潘悦, 王强, 曹怀刚, 高荪培. 水下弱目标跟踪的深度学习方法研究[J]. 兵工学报, 2024, 45(2): 385-394.
[4]	吕卫民, 孙晨峰, 任立坤, 赵杰, 李永强. 一种基于TCN-LGBM的航空发动机气路故障诊断方法[J]. 兵工学报, 2024, 45(1): 253-263.
[5]	秦昊林, 许廷发, 李佳男. 基于超像素注意力和孪生结构的半监督高光谱显著性目标检测[J]. 兵工学报, 2023, 44(9): 2639-2649.
[6]	彭沛然, 任术波, 李佳男, 周鸿伟, 许廷发. 基于光照感知的多光谱融合行人检测方法[J]. 兵工学报, 2023, 44(9): 2622-2630.
[7]	周宇, 曹荣刚, 栗苹, 马啸. 一种用于外场试验图像的引信炸点检测方法[J]. 兵工学报, 2023, 44(8): 2453-2464.
[8]	吴礼洋, 呙鹏程, 刘超, 李文强. 基于注意力机制增强残差网络的雷达信号调制类型识别[J]. 兵工学报, 2023, 44(8): 2310-2318.
[9]	刘懿, 任济寰, 吴祥, 薄煜明. 基于集成迁移学习的新装备装甲车辆分类[J]. 兵工学报, 2023, 44(8): 2319-2328.
[10]	何锦成, 韩永成, 张闻文, 何伟基, 陈钱. 基于通道校正卷积的真彩色微光图像增强[J]. 兵工学报, 2023, 44(6): 1643-1654.
[11]	刘佳, 刘海鸥, 陈慧岩, 毛飞鸿. 基于融合特征的无人履带车辆道路类型识别方法[J]. 兵工学报, 2023, 44(5): 1267-1276.
[12]	王检, 张邦宁, 张洁, 魏国峰, 郭道省. 基于多域特征融合的通信辐射源个体识别方法[J]. 兵工学报, 2023, 44(4): 949-959.
[13]	张良安, 陈洋, 谢胜龙, 刘同鑫. 基于机器视觉与深度学习的飞机防护栅裂纹检测系统[J]. 兵工学报, 2023, 44(2): 507-516.
[14]	王洋, 冯永新, 宋碧雪, 田秉禾. DP-DRCnet卷积神经网络信号调制识别算法[J]. 兵工学报, 2023, 44(2): 545-555.
[15]	郑志伟, 管雪元, 傅健, 马训穷, 尹上. 基于卷积神经网络与长短期记忆神经网络的弹丸轨迹预测[J]. 兵工学报, 2023, 44(10): 2975-2983.

基于深度学习的船体三维模型自动生成方法

3D Ship Model Generation Algorithm Based on Deep Learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价