基于距离视图表示与逐点细化结合的点云语义分割方法
Point cloud semantic segmentation based on range view representation and point-wise refinement
陈晗 1何鸿添 1雷印杰1
作者信息
- 1. 四川大学电子信息学院,成都 610065
- 折叠
摘要
三维点云语义分割是机器实现环境感知的重要途径.在现有的研究中,基于体素的算法和基于点的算法在面对大规模的点云数据时计算效率低下.而基于距离视图的算法,在对点云进行投影和反投影时会不可避免地造成精度损失.针对上述问题,提出了基于距离视图表示与逐点细化结合的点云语义分割新框架RPNet.充分的实验表明,所提出的方法在三维点云室外场景数据集SemanticKITTI上的平均交并比达到64.2%,推理速度达到58帧/秒,兼顾了高精度和高速度.
Abstract
3D point cloud semantic segmentation is an important way for machines to achieve environment awareness.In exist-ing research,voxel-based methods and point-based methods are computationally infficient in the face of large-scale point cloud data.And range-based methods inevitably cause accuracy loss when projecting and back projecting point clouds.To solve the above problems,this paper proposed RPNet,a noval 3D point cloud semantic segmentation framework based on range view repre-sentation and point-wise refinement.Sufficient experiments show that the proposed method achieves a mIoU of 64.2%and an infer-ence speed of 58 frames per second on the 3D point cloud outdoor scene dataset SemanticKITTI,balacing high accuracy and speed.
关键词
语义分割/三维点云/距离视图/逐点细化Key words
semantic segmentation/3D point cloud/range view/point-wise refinement引用本文复制引用
基金项目
国家自然科学基金面上项目(62276176)
出版年
2024
NETL
NSTL
维普
万方数据