Detail publikačního výsledku

CNN for Very Fast Ground Segmentation in Velodyne LiDAR Data

VEĽAS, M.; ŠPANĚL, M.; HRADIŠ, M.; HEROUT, A.

Originální název

CNN for Very Fast Ground Segmentation in Velodyne LiDAR Data

Anglický název

CNN for Very Fast Ground Segmentation in Velodyne LiDAR Data

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

This paper presents a novel method for ground segmentation in Velodyne point clouds. We propose an encoding of sparse 3D data from the Velodyne sensor suitable for training a convolutional neural network (CNN). This general purpose approach is used for segmentation of the sparse point cloud into ground and non-ground points. The LiDAR data are represented as a multi-channel 2D signal where the horizontal axis corresponds to the rotation angle and the vertical axis represents channels - laser beams. Multiple topologies of relatively shallow CNNs (i.e. 3-5 convolutional layers) are trained and evaluated, using a manually annotated dataset we prepared. The results show significant improvement of performance over the state-of-the-art method by Zhang et al. in terms of speed and also minor improvements in terms of accuracy.

Anglický abstrakt

This paper presents a novel method for ground segmentation in Velodyne point clouds. We propose an encoding of sparse 3D data from the Velodyne sensor suitable for training a convolutional neural network (CNN). This general purpose approach is used for segmentation of the sparse point cloud into ground and non-ground points. The LiDAR data are represented as a multi-channel 2D signal where the horizontal axis corresponds to the rotation angle and the vertical axis represents channels - laser beams. Multiple topologies of relatively shallow CNNs (i.e. 3-5 convolutional layers) are trained and evaluated, using a manually annotated dataset we prepared. The results show significant improvement of performance over the state-of-the-art method by Zhang et al. in terms of speed and also minor improvements in terms of accuracy.

Klíčová slova

convolutional neural networks, ground segmentation, Velodyne, LiDAR

Klíčová slova v angličtině

convolutional neural networks, ground segmentation, Velodyne, LiDAR

Autoři

VEĽAS, M.; ŠPANĚL, M.; HRADIŠ, M.; HEROUT, A.

Rok RIV

2020

Vydáno

27.04.2018

Nakladatel

Institute of Electrical and Electronics Engineers

Místo

Torres Vedras

ISBN

978-1-5386-5221-3

Kniha

IEEE International Conference on Autonomous Robot Systems and Competitions

Strany od

97

Strany do

103

Strany počet

7

URL

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8374167

BibTex

@inproceedings{BUT157178,
  author="Martin {Veľas} and Michal {Španěl} and Michal {Hradiš} and Adam {Herout}",
  title="CNN for Very Fast Ground Segmentation in Velodyne LiDAR Data",
  booktitle="IEEE International Conference on Autonomous Robot Systems and Competitions",
  year="2018",
  pages="97--103",
  publisher="Institute of Electrical and Electronics Engineers",
  address="Torres Vedras",
  doi="10.1109/ICARSC.2018.8374167",
  isbn="978-1-5386-5221-3",
  url="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8374167"
}

Dokumenty

ICRA18_0395_MS