摘要
针对反求工程中管道面重构问题,提出了一种从点云数据中直接提取管道面特征参数的算法.算法分为两步:第一步将管道面数据视为过渡特征数据,利用过渡特征提取原理获得管道面的一系列截面线,经概率统计方法进行噪声去除后,得到准确的截面线及其半径.第二步是由截面线的中心确定管道面的脊线点列.利用移动球法,球的直径即是采样步长,沿着脊线方向对点列进行均匀采样,然后对采样点列进行高斯平滑,获得光滑均匀的脊线点列.用三次B样条曲线拟合采样点列而获得脊线.计算实例表明,该方法能够稳定、准确地提取出管道面的几何特征参数.
For reconstruction of pipe surface in reverse engineering, an algorithm is proposed to directly extract geometric feature parameters of pipe surfaces from point cloud. This algorithm consists of two steps. In the first step, the point cloud of pipe surface was considered on as that of the blend surface. A series of profile curves of pipe surfaces were extracted based on the blend feature extraction method from point cloud and then the accurate profile curve and radius of pipe surfaces were determined by statistical analysis. In the second step, a set of points used to determine the spine curve was obtained by calculating the circular centers of the profile curves. These points were uniformly sampled by moving a sphere (with diameter being the sample step length), along the spine curve, and then the Gaussian method was used to smooth the sampled points. A spine Curve was fitted to those re-sampled points :with a cubic B-spline curve. Experiments illustrated that this algorithm can accurately and reliably extract the pipe surface from point cloud.
出处
《浙江大学学报(工学版)》
EI
CAS
CSCD
北大核心
2006年第5期768-771,857,共5页
Journal of Zhejiang University:Engineering Science
关键词
反求工程
特征提取
管道面
数据处理
reverse engineering
feature extraction
pipe surfaces
data processing