A Review on Point Cloud Semantic Segmentation Methods
MetadataShow full item record
Semantic segmentation of 3D point clouds is an open research problem and remains crucial for autonomous driving, robot navigation, human-computer interaction, 3D reconstruction and many others. The large scale of the data and lack of regular data organization make it a very complex task. Research in this ﬁeld focuses on point cloud representation (e.g., 2D images, 3D voxels grid, graph) and segmentation techniques. In the paper, state-of-the-art approaches related to these tasks are presented.