中文摘要：

为了同时提高点云平面分割效率与可靠性,提出了一种新的将区域增长与RANSAC相结合的点云平面分割方法。该方法通过对八叉树节点进行平面度测试实现种子平面的自动遴选,将节点平面参数作为区域增长约束得到初始分割结果。实验证明了该方法能够高效可靠地实现散乱点云平面分割。

英文摘要：

To improve the efficiency and reliability of plane segmentation for point cloud simultaneously,a novel segmentation approach with the combination of region growing andRANSAC is presented.For the automatic selection of the seed plane,the octree nodes areverified for their flatness,the parameters of which are using as the region growing constraintsto get the initial segmentation results.Then the nodes are checked for the need of further division and segmentation according to the initial results.The final results are gained after thepost-processing of merging and refining parameters using RANSAC.During the segmentationprocess,the computation of the points＇properties such as normal vector is not required.Theimplemented experiment shows that our method is efficient and robust.