Three-dimensional measurement of small mechanical parts under a complicated background based on stereo vision
Three-dimensional measurement of small mechanical parts under a complicated background based on stereo vision
复制标题
DOI：
10.1364/ao.49.001789
复制
发表时间：
2010-04-01
期刊：
影响因子：
1.9
通讯作者：
Cai, Lilong
中科院分区：
文献类型：
--
作者：
Ren, Zhiguo;Liao, Jiarui;Cai, Lilong
提出了一种基于立体视觉的复杂噪声背景下小工业零件三维精确测量的有效方法。为了有效地提取图像中被测零件所需曲线的非线性特征，基于虚拟运动控制系统，采用了从粗到精的提取策略。通过对灰度图像和虚拟波束链进行多尺度分解，可以准确地提取图像的非线性特征。通过分析几何误差的产生，提取所需曲线的精化特征点。这样就可以在最小二乘误差的情况下，准确地重建和测量被测零件的三维结构。实验结果表明，该方法能够准确测量由各种直线段和曲线表示的工业零件。(C)2010年美国光学学会
We present an effective method for the accurate three-dimensional (3D) measurement of small industrial parts under a complicated noisy background, based on stereo vision. To effectively extract the nonlinear features of desired curves of the measured parts in the images, a strategy from coarse to fine extraction is employed, based on a virtual motion control system. By using the multiscale decomposition of gray images and virtual beam chains, the nonlinear features can be accurately extracted. By analyzing the generation of geometric errors, the refined feature points of the desired curves are extracted. Then the 3D structure of the measured parts can be accurately reconstructed and measured with least squares errors. Experimental results show that the presented method can accurately measure industrial parts that are represented by various line segments and curves. (C) 2010 Optical Society of America