Point cloud data segmentation method of work surface based on RANSAC and octree voxel region growth
Konferenz: MEMAT 2022 - 2nd International Conference on Mechanical Engineering, Intelligent Manufacturing and Automation Technology
07.01.2022 - 09.01.2022 in Guilin, China
Tagungsband: MEMAT 2022
Seiten: 4Sprache: EnglischTyp: PDF
Autoren:
Dong, Bingqiang; Li, Janhua (School of Mechanical & Electronical Engineering, Lanzhou University of Technology, Lanzhou, Gansu, China)
Ban, Jianfeng (School of Mechanical & Electronical Engineering, Lanzhou University of Technology, Lanzhou, Gansu, China & Chalco Steering Intelligent Technology Co., Ltd, Changsha, Hunan, China)
Inhalt:
In response to the recognition requirements of the point cloud data of the job surface, a hybrid segmentation method of the job surface point cloud data based on RANSAC and octree voxel region growth is proposed. The method uses RANSAC to segment the job surface from multiple point cloud surface data. Point cloud data, and then voxelize the point cloud data, perform octree voxel structure dissection, and use the area growth segmentation based on octree voxels to obtain the point cloud data of the operation surface, thereby effectively removing the edge noise data of the operation surface, To achieve the purpose of precise segmentation, the effectiveness of the method is proved through the identification experiment of the alloy casting ingot machining surface.