3D Large-Scale Point Cloud Semantic Segmentation Using Optimal Feature Description Vector Network: OFDV-Net
Efficient semantic segmentation of large-scale 3D point clouds is a fundamental and essential capability for real-time intelligent systems, such as autonomous driving and augmented reality. The high dimension feature vector and the complex network structure are two major constraints to utilize the l...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9291411/ |
id |
doaj-3f5a038c4a7341cfae59459ed1133f21 |
---|---|
record_format |
Article |
spelling |
doaj-3f5a038c4a7341cfae59459ed1133f212021-03-30T04:25:13ZengIEEEIEEE Access2169-35362020-01-01822628522629610.1109/ACCESS.2020.304416692914113D Large-Scale Point Cloud Semantic Segmentation Using Optimal Feature Description Vector Network: OFDV-NetJian Li0https://orcid.org/0000-0001-8976-6624Quan Sun1https://orcid.org/0000-0001-8248-2098Keru Chen2https://orcid.org/0000-0001-7036-0253Hao Cui3https://orcid.org/0000-0001-9378-012XKuan Huangfu4https://orcid.org/0000-0001-6861-8788Xiaolong Chen5https://orcid.org/0000-0002-2515-5004School of the Geo-Science and Technology, Zhengzhou University, Zhengzhou, ChinaSchool of Water Conservancy Science and Engineering, Zhengzhou University, Zhengzhou, ChinaSchool of Water Conservancy Science and Engineering, Zhengzhou University, Zhengzhou, ChinaSchool of the Geo-Science and Technology, Zhengzhou University, Zhengzhou, ChinaSchool of Water Conservancy Science and Engineering, Zhengzhou University, Zhengzhou, ChinaSchool of Water Conservancy Science and Engineering, Zhengzhou University, Zhengzhou, ChinaEfficient semantic segmentation of large-scale 3D point clouds is a fundamental and essential capability for real-time intelligent systems, such as autonomous driving and augmented reality. The high dimension feature vector and the complex network structure are two major constraints to utilize the large-scale point cloud. This paper proposes an optimal feature description vector network (OFDV-Net) for 3D point cloud semantic segmentation. First, a multiscale point cloud feature extraction structure is constructed to generate an initial feature description vector (IFDV). Then, IFDV is selected by a feature selection unit to obtain the optimal feature description vector (OFDV). The OFDV encapsulates the best 3D features set of the points and can be used as the input of the deep neural network for training and testing. Finally, the OFDV-Net was applied to the standard public outdoor large-scale point cloud datasets Semantic3D and NPM3D, and the overall segmentation accuracy of 88.3% and 87.7% were obtained, respectively; moreover, the OFDV-Net requires less training time, which indicates that the algorithm can obtain high-precision semantic segmentation results on an outdoor large-scale point cloud while reducing model training time.https://ieeexplore.ieee.org/document/9291411/Optimal feature description vectorpoint cloudfeature selectionsemantic segmentationdeep learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jian Li Quan Sun Keru Chen Hao Cui Kuan Huangfu Xiaolong Chen |
spellingShingle |
Jian Li Quan Sun Keru Chen Hao Cui Kuan Huangfu Xiaolong Chen 3D Large-Scale Point Cloud Semantic Segmentation Using Optimal Feature Description Vector Network: OFDV-Net IEEE Access Optimal feature description vector point cloud feature selection semantic segmentation deep learning |
author_facet |
Jian Li Quan Sun Keru Chen Hao Cui Kuan Huangfu Xiaolong Chen |
author_sort |
Jian Li |
title |
3D Large-Scale Point Cloud Semantic Segmentation Using Optimal Feature Description Vector Network: OFDV-Net |
title_short |
3D Large-Scale Point Cloud Semantic Segmentation Using Optimal Feature Description Vector Network: OFDV-Net |
title_full |
3D Large-Scale Point Cloud Semantic Segmentation Using Optimal Feature Description Vector Network: OFDV-Net |
title_fullStr |
3D Large-Scale Point Cloud Semantic Segmentation Using Optimal Feature Description Vector Network: OFDV-Net |
title_full_unstemmed |
3D Large-Scale Point Cloud Semantic Segmentation Using Optimal Feature Description Vector Network: OFDV-Net |
title_sort |
3d large-scale point cloud semantic segmentation using optimal feature description vector network: ofdv-net |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Efficient semantic segmentation of large-scale 3D point clouds is a fundamental and essential capability for real-time intelligent systems, such as autonomous driving and augmented reality. The high dimension feature vector and the complex network structure are two major constraints to utilize the large-scale point cloud. This paper proposes an optimal feature description vector network (OFDV-Net) for 3D point cloud semantic segmentation. First, a multiscale point cloud feature extraction structure is constructed to generate an initial feature description vector (IFDV). Then, IFDV is selected by a feature selection unit to obtain the optimal feature description vector (OFDV). The OFDV encapsulates the best 3D features set of the points and can be used as the input of the deep neural network for training and testing. Finally, the OFDV-Net was applied to the standard public outdoor large-scale point cloud datasets Semantic3D and NPM3D, and the overall segmentation accuracy of 88.3% and 87.7% were obtained, respectively; moreover, the OFDV-Net requires less training time, which indicates that the algorithm can obtain high-precision semantic segmentation results on an outdoor large-scale point cloud while reducing model training time. |
topic |
Optimal feature description vector point cloud feature selection semantic segmentation deep learning |
url |
https://ieeexplore.ieee.org/document/9291411/ |
work_keys_str_mv |
AT jianli 3dlargescalepointcloudsemanticsegmentationusingoptimalfeaturedescriptionvectornetworkofdvnet AT quansun 3dlargescalepointcloudsemanticsegmentationusingoptimalfeaturedescriptionvectornetworkofdvnet AT keruchen 3dlargescalepointcloudsemanticsegmentationusingoptimalfeaturedescriptionvectornetworkofdvnet AT haocui 3dlargescalepointcloudsemanticsegmentationusingoptimalfeaturedescriptionvectornetworkofdvnet AT kuanhuangfu 3dlargescalepointcloudsemanticsegmentationusingoptimalfeaturedescriptionvectornetworkofdvnet AT xiaolongchen 3dlargescalepointcloudsemanticsegmentationusingoptimalfeaturedescriptionvectornetworkofdvnet |
_version_ |
1724181858193768448 |