Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/106305
Title: | PointMoSeg : sparse tensor-based end-to-end moving-obstacle segmentation in 3-D lidar point clouds for autonomous driving | Authors: | Sun, Y Zuo, W Huang, H Cai, P Liu, M |
Issue Date: | Apr-2021 | Source: | IEEE robotics and automation letters, Apr. 2021, v. 6, no. 2, p. 510-517 | Abstract: | Moving-obstacle segmentation is an essential capability for autonomous driving. For example, it can serve as a fundamental component for motion planning in dynamic traffic environments. Most of the current 3-D Lidar-based methods use road segmentation to find obstacles, and then employ ego-motion compensation to distinguish the static or moving states of the obstacles. However, when there is a slope on a road, the widely-used flat-road assumption for road segmentation may be violated. Moreover, due to the signal attenuation, GPS-based ego-motion compensation is often unreliable in urban environments. To provide a solution to these issues, this letter proposes an end-to-end sparse tensor-based deep neural network for moving-obstacle segmentation without using GPS or the planar-road assumption. The input to our network are merely two consecutive (previous and current) point clouds, and the output is directly the point-wise mask for moving obstacles on the current frame. We train and evaluate our network on the public nuScenes dataset. The experimental results confirm the effectiveness of our network and the superiority over the baselines. | Keywords: | 3-D Lidar Autonomous driving End-to-end Moving obstacle Point cloud Sparse tensor |
Publisher: | Institute of Electrical and Electronics Engineers | Journal: | IEEE robotics and automation letters | EISSN: | 2377-3766 | DOI: | 10.1109/LRA.2020.3047783 | Rights: | © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The following publication Y. Sun, W. Zuo, H. Huang, P. Cai and M. Liu, "PointMoSeg: Sparse Tensor-Based End-to-End Moving-Obstacle Segmentation in 3-D Lidar Point Clouds for Autonomous Driving," in IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 510-517, April 2021 is available at https://doi.org/10.1109/LRA.2020.3047783. |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Sun_Pointmoseg_Sparse_Tensor-Based.pdf | Pre-Published version | 3.56 MB | Adobe PDF | View/Open |
Page views
8
Citations as of Jun 30, 2024
Downloads
2
Citations as of Jun 30, 2024
SCOPUSTM
Citations
15
Citations as of Jul 4, 2024
WEB OF SCIENCETM
Citations
13
Citations as of Jul 4, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.