A Fast Point Cloud Segmentation Algorithm Based on Region Growth

Point cloud segmentation is a key prerequisite for object classification recognition. We propose a fast region growing algorithm by using the neighborhood search, filter sampling, Euclidean clustering and region growth. Segmentation experiment on point cloud data in indoor environment demonstrated that segmentation accuracy and efficiency were improved by the proposed algorithm.

[1]  Junjie Zhang,et al.  A 3D Point Cloud Segmentation Method Based on Local Convexity and Dimension Features , 2018, 2018 Chinese Control And Decision Conference (CCDC).

[2]  Qijun J. Chen,et al.  A graph-based plane segmentation approach for noisy point clouds , 2013, 2013 25th Chinese Control and Decision Conference (CCDC).

[3]  Abdul Nurunnabi,et al.  Robust Segmentation for Large Volumes of Laser Scanning Three-Dimensional Point Cloud Data , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Dong Yin,et al.  A fast segmentation method of sparse point clouds , 2017, 2017 29th Chinese Control And Decision Conference (CCDC).

[5]  Anh Nguyen,et al.  3D point cloud segmentation: A survey , 2013, 2013 6th IEEE Conference on Robotics, Automation and Mechatronics (RAM).

[6]  Markus Vincze,et al.  Segmentation of unknown objects in indoor environments , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.