Please wait a minute...
IET Cyber-Systems and Robotics
IET Cyber-Systems and Robotics  2022, Vol. 4 Issue (2): 107-115    DOI: 10.1049/csy2.12047
    
LessNet: Lightweight and efficient semantic segmentation for large-scale point clouds
LessNet: Lightweight and efficient semantic segmentation for large-scale point clouds
 全文: PDF 
摘要： With a wide range of applications in autonomous driving and robotics, semantic segmentation for large-scale outdoor point clouds is a critical and challenging issue. Due to the large number and irregular arrangement of point clouds, it is difficult to balance the efficiency and effectiveness. In this paper, we propose LessNet, a lightweight and efficient voxel-based method for LiDAR-only semantic segmentation, taking advantage of cylindrical partition and intra-voxel feature fusion. Specifically, we use a cylindrical partition method to distribute the outdoor point clouds more evenly in voxels. To better encode the voxel features, we adopt an intra-voxel aggregation method without querying neighbours. The voxel features are further input into a lightweight and effective 3D U-net to aggregate local features and dilate the receptive field. Extensive experiments prove the satisfied semantic segmentation performance and the improvement of each component in our proposed framework. Our method is capable of processing more than one million point clouds at a time while retaining low latency and few parameters. Moreover, our method achieves comparable performance with state-of-the-art approaches and outperforms all projection-based methods on the SemanticKITTI benchmark.
Abstract: With a wide range of applications in autonomous driving and robotics, semantic segmentation for large-scale outdoor point clouds is a critical and challenging issue. Due to the large number and irregular arrangement of point clouds, it is difficult to balance the efficiency and effectiveness. In this paper, we propose LessNet, a lightweight and efficient voxel-based method for LiDAR-only semantic segmentation, taking advantage of cylindrical partition and intra-voxel feature fusion. Specifically, we use a cylindrical partition method to distribute the outdoor point clouds more evenly in voxels. To better encode the voxel features, we adopt an intra-voxel aggregation method without querying neighbours. The voxel features are further input into a lightweight and effective 3D U-net to aggregate local features and dilate the receptive field. Extensive experiments prove the satisfied semantic segmentation performance and the improvement of each component in our proposed framework. Our method is capable of processing more than one million point clouds at a time while retaining low latency and few parameters. Moreover, our method achieves comparable performance with state-of-the-art approaches and outperforms all projection-based methods on the SemanticKITTI benchmark.
出版日期: 2022-07-22
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Guoqiang Feng
Weilong Li
Xiaolin Zhao
Xuemeng Yang
Xin Kong
TianXin Huang
Jinhao Cui

引用本文:

Guoqiang Feng, Weilong Li, Xiaolin Zhao, Xuemeng Yang, Xin Kong, TianXin Huang, Jinhao Cui. LessNet: Lightweight and efficient semantic segmentation for large-scale point clouds. IET Cyber-Systems and Robotics, 2022, 4(2): 107-115.

链接本文:

https://www.zjujournals.com/iet-csr/CN/10.1049/csy2.12047    或    https://www.zjujournals.com/iet-csr/CN/Y2022/V4/I2/107

No related articles found!