期刊文献+

基于PointNet的车身分割方法 被引量:3

Segmentation method of car body based on PointNet
原文传递
导出
摘要 多视图参数化重构方法对车身拓扑优化结果进行重构时需将车身分割为多个独立部分,以达到分割后拓扑优化车身各部分可独立进行重构的目的。对以车身点云作为输入的分割方法进行研究,采用深度学习理论对PointNet网络框架进行改进,根据车身拓扑优化结果,基于多视图参数化重构方法将车身分割为多个部分并赋予标签,并使用CAD(computer aided design)制作及点云增强操作得到车身分割点云数据集,通过梯度下降算法对网络模型进行训练。最终,车身分割网络模型在车身点云测试集中的准确率为87.7%。 The multi-view parametric reconstruction method needs to divide the car body into multiple independent parts to reconstruct the result of car body topology optimization,so that each part of the topology optimized car body can be reconstructed independently after segmentation.The intelligent segmentation method of car body point cloud as input is studied,and the deep learning theory is used to improve the PointNet network framework.The car body is divided into several parts and given labels based on multi-view parametric reconstruction method according to the body topology optimization result contents.The car body segmentation point cloud data set is obtained by CAD(computer aided design)production and point cloud enhancement operation,and the network model is trained by gradient descent algorithm.Finally,the car body segmentation network model achieves 87.7%accuracy in the car body point cloud test set.
作者 阮剑 朱连海 胡三宝 RUAN Jian;ZHU Lianhai;HU Sanbao(Hubei Key Laboratory of Advanced Technology for Automotive Conponents,Wuhan University of Technology,Wuhan 430070,China;Hubei Collaborative Innovation Center for Automotive Components Technology,Wuhan University of Technology,Wuhan 430070,China;Bohai Shipbuilding Heavy Industry Co.,Ltd.,Huludao 125005,China)
出处 《武汉大学学报(工学版)》 CAS CSCD 北大核心 2023年第3期347-352,共6页 Engineering Journal of Wuhan University
基金 国家自然科学基金资助项目(编号:51305314)。
关键词 承载式车身 几何重构 点云分割 深度学习 PointNet load-bearing body geometry reconstruction point cloud segmentation deep learning PointNet
  • 相关文献

参考文献2

二级参考文献16

  • 1Yi D R, Hayward V. Skeletonization of volumetric angiorams for display[J]. Computer Methods in Biomethanics and Biomedical Engineering, 2002, 5(5): 329-341.
  • 2Siddiqi K, Bouix S, Tannenbaum A, et al. The Hamilton-Jacobi skeleton[EB/OL]. Http://www.cg.its.tudelft.nl/wwwsv/publications/reinders2000.pdf.
  • 3Reinders F, Jacobson M E D, Post F H. Skeleton graph generation for feature shape description[A]. Proceedings of the 2nd Joint Eurographics and IEEE TCVG Symposium on Visualization[C]. Amsterdam, Netherlands:Springer, 2000. 73~82.
  • 4Zhou Y, Toga A W. Efficient skeletonization of volumetric objects[J]. IEEE Transactions on Visualization and Computer Graphics, 1999, 5(3):196-209.
  • 5Ogniewicz R L, Kubler O. Hierarchic Voronoi skeletons[J]. Pattern Recognition, 1995, 28(3): 343-359.
  • 6Ma W C, Wu F C, Ouhyoung M. Skeleton extraction of 3D objects with radial basis functions[A]. Proceedings of Shape Modeling International 2003[C]. Los Alamitos, CA, USA:IEEE Computer Society, 2003. 207-215.
  • 7Huang J, Yagel R, Fillipov V, et al. An accurate method for voxelizing polygon meshes[A]. IEEE Symposium on Volume Visualization[C]. New York, NY,USA:IEEE, 1998. 119-126.
  • 8Rosenfeld A, Pfaltz J L. Sequential operations in digital picture processing[J]. Journal of the ACM, 1966,13(4): 471-494.
  • 9Borgefors G. Distance transformations in arbitrary dimension[J]. Computer Vision, Graphics, and Image Processsing,1984, 27(3): 321-345.
  • 10Danielsson P E. Euclidean distance mapping[J]. Computer Graphics and Image Processing, 1980, 14(3): 227-248.

共引文献6

同被引文献18

引证文献3

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部