• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>North American Manufacturing Research Conference >Efficient Algorithms for Automated Inspection of Freeform Surfaces
【24h】

Efficient Algorithms for Automated Inspection of Freeform Surfaces

机译：自动检查自动检查的高效算法

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper reports the development of efficient algorithms for automated inspection of freeform surfaces using point cloud data collected using an inspection system. The registration process to align the point cloud with the input CAD surface model is carried out in two phases, viz, rough registration followed by an accurate (fine) registration. For rough registration, algorithms based on the bounding box method and the convex hull method have been proposed. Fine registration is carried out using a computational geometry approach using a tessellated representation of the surface model. A random sampling technique has been integrated with the final registration algorithm to speed up the registration process. The algorithms have been compared with those reported in literature. Results show that the proposed algorithms substantially reduce the computational time, without sacrificing the accuracy of registration.
机译：本文报告了使用使用检测系统收集的点云数据的自动检查自动检查有效算法的开发。将点云与输入CAD表面模型对齐点云的注册过程由两个阶段，viz，粗略注册，然后是准确的（细）注册。对于粗略的注册，已经提出了基于边界框方法和凸壳方法的算法。使用使用表面模型的镶嵌表示使用计算几何方法进行精细注册。随机采样技术已与最终注册算法集成，以加快注册过程。将该算法与文学中报告的那些进行了比较。结果表明，所提出的算法大大减少了计算时间，而不牺牲登记的准确性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号