摘要
在利用三维激光扫描仪获取薄煤层三维点云数据的基础上,为了检测出薄煤层掘进窗口,采用了一种利用三维点云数据局部微分性质,包括法向量以及曲率,来进行三维边缘检测的方法。首先,使用最小二乘法计算出各点的法向量和曲率;再利用法向量进行统计分析筛选出候选边缘点,最后采用区域生长算法对候选边缘点进行分割,从而判断各点是否为边缘点。实验证明该方法能够快速有效的检测出边缘点。
In order to detect the heading window in the 3D point cloud of thin seam obtained by a 3D laser scanner, a 3D edge detection method that utilize a partial differential properties of a 3D point cloud data utilization, including the normal vector and curvature, is introduced. Firstly, the normal vector and curvature at each point are calculated using the least squares method; Then statistical analysis on normal vector and filter candidate edge points, and finally using region growing algorithm divides the candidate edge points, in order to determine whether a point is an edge point. Experiments show that this method can quickly and efficiently detect the edge points.
出处
《计算机与数字工程》
2015年第9期1659-1661,1673,共4页
Computer & Digital Engineering
关键词
法向量
曲率
区域增长
边缘检测
normal vector, curvature, region growing, edge detection
