Temporal feature matching and propagation for semantic segmentation on 3D point cloud sequences

In real-world LiDAR-based applications, data is generated in the form of 3D point cloud sequences or 4D point clouds. However, the topic of semantic segmentation on 4D point clouds is under-investigated and existing methods are still not able to achieve satisfactory performance to meet the requi...

Full description

Saved in:
Bibliographic Details
Main Authors: Shi, Hanyu, Li, Ruibo, Liu, Fayao, Lin, Guosheng
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/10356/172229
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-172229
record_format dspace
spelling sg-ntu-dr.10356-1722292023-12-08T15:35:53Z Temporal feature matching and propagation for semantic segmentation on 3D point cloud sequences Shi, Hanyu Li, Ruibo Liu, Fayao Lin, Guosheng School of Computer Science and Engineering Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence 4D Point Clouds Semantic Segmentation In real-world LiDAR-based applications, data is generated in the form of 3D point cloud sequences or 4D point clouds. However, the topic of semantic segmentation on 4D point clouds is under-investigated and existing methods are still not able to achieve satisfactory performance to meet the requirement for real-world applications. The temporal information across different point clouds plays an important role in dynamic scene understanding, which is not well explored in existing work. In this paper, we focus on exploring effective temporal information across two consecutive point clouds for semantic segmentation on point cloud sequences. To this end, we design three novel modules to enhance the features of target frames by extracting different temporal information in the local regions and global regions. Experimental results on SemanticKITTI and SemanticPOSS demonstrate that our method achieves superior performance in 4D semantic segmentation by utilizing temporal information. Agency for Science, Technology and Research (A*STAR) AI Singapore Ministry of Education (MOE) National Research Foundation (NRF) Submitted/Accepted version This research is supported by the MoE AcRF Tier 2 grant (MOE-T2EP20220-0007) and MoE AcRF Tier 1 grants (RG14/22, RG95/20), and the National Research Foundation, Singapore under its AI Singapore Programme (AISG Award No: AISG-RP-2018-003). This research is also supported by the Agency for Science, Technology and Research (A*STAR), Singapore under its MTC Young Individual Research Grant (Grant No. M21K3c0130). 2023-12-05T02:06:34Z 2023-12-05T02:06:34Z 2023 Journal Article Shi, H., Li, R., Liu, F. & Lin, G. (2023). Temporal feature matching and propagation for semantic segmentation on 3D point cloud sequences. IEEE Transactions On Circuits and Systems for Video Technology. https://dx.doi.org/10.1109/TCSVT.2023.3273546 1051-8215 https://hdl.handle.net/10356/172229 10.1109/TCSVT.2023.3273546 en MOE-T2EP20220-0007 RG14/22 RG95/20 AISG-RP-2018-003 M21K3c0130 IEEE Transactions on Circuits and Systems for Video Technology © 2023 IEEE. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1109/TCSVT.2023.3273546. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
4D Point Clouds
Semantic Segmentation
spellingShingle Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
4D Point Clouds
Semantic Segmentation
Shi, Hanyu
Li, Ruibo
Liu, Fayao
Lin, Guosheng
Temporal feature matching and propagation for semantic segmentation on 3D point cloud sequences
description In real-world LiDAR-based applications, data is generated in the form of 3D point cloud sequences or 4D point clouds. However, the topic of semantic segmentation on 4D point clouds is under-investigated and existing methods are still not able to achieve satisfactory performance to meet the requirement for real-world applications. The temporal information across different point clouds plays an important role in dynamic scene understanding, which is not well explored in existing work. In this paper, we focus on exploring effective temporal information across two consecutive point clouds for semantic segmentation on point cloud sequences. To this end, we design three novel modules to enhance the features of target frames by extracting different temporal information in the local regions and global regions. Experimental results on SemanticKITTI and SemanticPOSS demonstrate that our method achieves superior performance in 4D semantic segmentation by utilizing temporal information.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Shi, Hanyu
Li, Ruibo
Liu, Fayao
Lin, Guosheng
format Article
author Shi, Hanyu
Li, Ruibo
Liu, Fayao
Lin, Guosheng
author_sort Shi, Hanyu
title Temporal feature matching and propagation for semantic segmentation on 3D point cloud sequences
title_short Temporal feature matching and propagation for semantic segmentation on 3D point cloud sequences
title_full Temporal feature matching and propagation for semantic segmentation on 3D point cloud sequences
title_fullStr Temporal feature matching and propagation for semantic segmentation on 3D point cloud sequences
title_full_unstemmed Temporal feature matching and propagation for semantic segmentation on 3D point cloud sequences
title_sort temporal feature matching and propagation for semantic segmentation on 3d point cloud sequences
publishDate 2023
url https://hdl.handle.net/10356/172229
_version_ 1784855584654229504