期刊文献+

基于形状特征的管路接头测量和三维重建方法 被引量:4

Measurement and 3D reconstruction method for pipeline's joints based on shape feature
下载PDF
导出
摘要 针对复杂管路系统中的接头同步测量和三维重建的难题,提出一种基于形状特征的管路接头测量和三维重建方法。该方法通过接头CAD模型边缘轮廓和实物图像边缘轮廓进行形状特征匹配来实现接头空间位姿的测量。首先通过建立虚拟相机"视点球"获取接头CAD模型边缘轮廓的投影图像,经过金字塔分层组成接头的形状特征图库;然后与获取的接头实物图像边缘轮廓进行对比匹配;最后利用最小二乘法迭代求解接头的空间位姿,并重建接头的三维模型。开发了管路多目视觉测量系统并进行了接头位姿测量和管路三维重建实验,实验表明该方法的接头测量和三维重建时间可控制在1min内,位置误差为0.654mm,姿态误差为0.73°,测量和重建的效率与精度满足工程要求。 To resolve the problem of joint's synchronous measurement and reconstruction in complex pipeline system,a measurement and 3Dreconstruction method for pipeline's joints based on shape feature was proposed.A shape feature matching between contours of joint's CAD model and those of joint's material object was adopted to realize the measurement of joint's spatial pose.Projected images of joint's CAD model were acquired through setting up'sphere of viewpoints'of virtual cameras.These projected images were layered in the pyramidal structure to compose a gallery of matching images,and the joint's edges images acquired from material object were matched with its matching images.The joint's spatial pose was calculated iteratively by the least square method,and the joint's 3Dmodel in the pipeline system was reconstructed.A pipeline multi-camera measurement system was proposed,and the experiments on a pipeline's joint pose measurement and 3Dreconstruction were carried out.The result showed that the measurement and reconstruction time could be controlled within 1minute,the position and rotation error were respectively0.654 mm and 0.73°.The efficiency and accuracy of the proposed measurement and reconstruction method could meet the engineering requirements.
出处 《计算机集成制造系统》 EI CSCD 北大核心 2015年第1期123-134,共12页 Computer Integrated Manufacturing Systems
基金 国家自然科学基金资助项目(51305031)~~
关键词 管路接头 位姿测量 三维重建 形状特征 CAD模型 pipeline joint pose measurement 3Dreconstruction shape feature computer aided design model
  • 相关文献

参考文献12

  • 1Mauro S. Costa,Linda G. Shapiro.3D Object Recognition and Pose with Relational Indexing[J]. Computer Vision and Image Understanding . 2000 (3)
  • 2J.H.M. Byne,J.A.D.W. Anderson.A CAD-based computer vision system[J]. Image and Vision Computing . 1998 (8)
  • 3Jose A. Ventura,Wenhua Wan.Accurate matching of two-dimensional shapes using the minimal tolerance zone error[J]. Image and Vision Computing . 1997 (12)
  • 4Michael S. Paterson,F. Frances Yao.Efficient binary space partitions for hidden-surface removal and solid modeling[J]. Discrete & Computational Geometry . 1990 (1)
  • 5Mohannad Gharavi-Alkhansari.A fast globally optimal algorithm for template matching using low-resolution pruning. IEEE Transactions on Image Processing . 2001
  • 6Y Hel-Or,H Hel-Or.Real-time pattern matching using projection kernels. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2005
  • 7Olson C F,Huttenlocher D P.Automatic target recognition by matching oriented edge pixels. IEEE Transactions on Image Processing . 1997
  • 8Lamdan Y,Schwartz J T,Wolfson H J.Affine invariant model-based object recognition. IEEE Transactions on Robotics and Automation . 1990
  • 9Canny J.A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1986
  • 10C. M. Cyr,and B. B. Kimia.3D object recognition using shape similarity-based aspect graph. Proceedings of 8th IEEE International Conference on Computer Vision . 2001

共引文献1

同被引文献33

引证文献4

二级引证文献8

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