Page 7 - Read Online

Wu et al. Intell Robot 2022;2(2):105­29 Intelligence & Robotics
DOI: 10.20517/ir.2021.20

Review Open Access

Deep learning for LiDAR-only and LiDAR-fusion 3D
perception: a survey

Danni Wu, Zichen Liang, Guang Chen
School of Automotive Studies, Tongji University, Shanghai 201804, China.

Correspondence to: Prof. Guang Chen, School of Automotive Studies, Tongji University, 4800 Caoan Road, Shanghai 201804,
China. E-mail: guangchen@tongji.edu.cn
How to cite this article: Wu D, Liang Z, Chen G. Deep learning for LiDAR-only and LiDAR-fusion 3D perception: a survey. Intell
Robot 2022;2(2):105-29. http://dx.doi.org/10.20517/ir.2021.20

Received: 31 Dec 2021 First Decision: 25 Feb 2022 Revised: 10 Mar 2022 Accepted: 16 Mar 2022 Published: 25 Apr 2022
Academic Editors: Simon X. Yang, Lei Lei Copy Editor: Jin-Xin Zhang Production Editor: Jin-Xin Zhang

Abstract
The perception system for robotics and autonomous cars relies on the collaboration among multiple types of sensors
to understand the surrounding environment. LiDAR has shown great potential to provide accurate environmental
information, and thus deep learning on LiDAR point cloud draws increasing attention. However, LiDAR is unable to
handle severe weather. The sensor fusion between LiDAR and other sensors is an emerging topic due to its sup-
plementary property compared to a single LiDAR. Challenges exist in deep learning methods that take LiDAR point
cloud fusion data as input, which need to seek a balance between accuracy and algorithm complexity due to data
redundancy. This work focuses on a comprehensive survey of deep learning on LiDAR-only and LiDAR-fusion 3D
perception tasks. Starting with the representation of LiDAR point cloud, this paper then introduces its unique char-
acteristics and the evaluation dataset as well as metrics. This paper gives a review according to four key tasks in the
field of LiDAR-based perception: object classification, object detection, object tracking, and segmentation (includ-
ing semantic segmentation and instance segmentation). Finally, we present the overlooked aspects of the current
algorithms and possible solutions, hoping this paper can serve as a reference for the related research.

Keywords: LiDAR, sensor fusion, object classification, object detection, object tracking, segmentation

© The Author(s) 2022. Open Access This article is licensed under a Creative Commons Attribution 4.0
International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, shar­
ing, adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as long as you
give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate
if changes were made.

www.intellrobot.com