research-article

Strategic Improvements of SqueezeSegV2 for Road-Scene Semantic Segmentation Using 3D LiDAR Point Cloud

Authors:

Quoc-Hung Tran,

Thien Huynh-TheAuthors Info & Claims

SOICT '23: Proceedings of the 12th International Symposium on Information and Communication Technology

Pages 463 - 470

https://doi.org/10.1145/3628797.3628915

Published: 07 December 2023 Publication History

Abstract

Semantic segmentation of LiDAR point clouds for road-scene analysis in autonomous vehicles and driver assistance systems is a challenging task due to the confusion of categories and the sparse distribution of point clouds, thus leading low performance. In this paper, we propose two important improvements to SqueezeSegV2, a deep encoder-decoder neural network, to improve the overall performance of semantic segmentation. The first improvement is the adaptive Fire module, which can be configured to be lightweight or accurate, depending on the service and application requirements. The second one is the steady Fire Deconvolution module, which boosts the accuracy of the segmentation mask reconstruction. Remarkably, both modules are improved by apply manipulating the combination of symmetric and asymmetric grouped convolution with dilation rate to enhance the contextual learning efficiency of the deep model. We evaluate our proposed methods on the Panda dataset and show that they achieve better segmentation accuracy than the original SqueezeSegV2 model by mean accuracy and mean IoU, while also reducing the number of trainable parameters by around .

References

[1]

Pierre Biasutti, Aurélie Bugeau, Jean-François Aujol, and Mathieu Brédif. 2019. RIU-Net: Embarrassingly simple semantic segmentation of 3D LiDAR point cloud. arXiv preprint arXiv:1905.08748 (2019), 1–5.

[2]

Gabriela Csurka, Diane Larlus, Florent Perronnin, and France Meylan. 2013. What is a good evaluation measure for semantic segmentation?. In 24th British Machine Vision Conference (BMVC). BMVA, Bristol, UK, 10–5244.

[3]

Bertrand Douillard, James Underwood, Noah Kuntz, Vsevolod Vlaskine, Alastair Quadros, Peter Morton, and Alon Frenkel. 2011. On the segmentation of 3D LIDAR point clouds. In 2011 IEEE International Conference on Robotics and Automation. IEEE, Shanghai, China, 2798–2805.

[4]

Qingyong Hu, Bo Yang, Linhai Xie, Stefano Rosa, Yulan Guo, Zhihua Wang, Niki Trigoni, and Andrew Markham. 2020. Randla-net: Efficient semantic segmentation of large-scale point clouds. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. IEEE, Seattle, WA, USA, 11108–11117.

[5]

Georg Krispel, Michael Opitz, Georg Waltner, Horst Possegger, and Horst Bischof. 2020. Fuseseg: Lidar point cloud segmentation fusing multi-modal data. In Proceedings of the IEEE/CVF winter conference on applications of computer vision. IEEE, Snowmass, CO, USA, 1874–1883.

[6]

Ying Li, Lingfei Ma, Zilong Zhong, Fei Liu, Michael A Chapman, Dongpu Cao, and Jonathan Li. 2020. Deep learning for lidar point clouds in autonomous driving: A review. IEEE Transactions on Neural Networks and Learning Systems 32, 8 (2020), 3412–3432.

[7]

Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2020. Focal Loss for Dense Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 42, 2 (2020), 318–327. https://doi.org/10.1109/TPAMI.2018.2858826

[8]

Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. 2017. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems 30 (2017), 5099–5108.

[9]

Vazgen Vanian, Georgios Zamanakos, and Ioannis Pratikakis. 2022. Improving performance of deep learning models for 3D point cloud semantic segmentation via attention mechanisms. Computers & Graphics 106 (2022), 277–287.

Digital Library

[10]

Yuan Wang, Tianyue Shi, Peng Yun, Lei Tai, and Ming Liu. 2018. Pointseg: Real-time semantic segmentation based on 3d lidar point cloud. arXiv preprint arXiv:1807.06288 (2018), 1–7.

[11]

Bichen Wu, Alvin Wan, Xiangyu Yue, and Kurt Keutzer. 2018. Squeezeseg: Convolutional neural nets with recurrent crf for real-time road-object segmentation from 3d lidar point cloud. In 2018 IEEE international conference on robotics and automation (ICRA). IEEE, Brisbane, QLD, Australia, 1887–1893.

Digital Library

[12]

Bichen Wu, Xuanyu Zhou, Sicheng Zhao, Xiangyu Yue, and Kurt Keutzer. 2019. Squeezesegv2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a lidar point cloud. In 2019 international conference on robotics and automation (ICRA). IEEE, Montreal, QC, Canada, 4376–4382.

Digital Library

[13]

Pengchuan Xiao, Zhenlei Shao, Steven Hao, Zishuo Zhang, Xiaolin Chai, Judy Jiao, Zesong Li, Jian Wu, Kai Sun, Kun Jiang, 2021. Pandaset: Advanced sensor suite dataset for autonomous driving. In 2021 IEEE International Intelligent Transportation Systems Conference (ITSC). IEEE, Indianapolis, IN, USA, 3095–3101.

Digital Library

[14]

Pengcheng Zhang, Huagui He, Yun Wang, Yang Liu, Hong Lin, Liang Guo, and Weijun Yang. 2022. 3D urban buildings extraction based on airborne lidar and photogrammetric point cloud fusion according to U-Net deep learning model segmentation. IEEE Access 10 (2022), 20889–20897.

[15]

Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, and Jian Sun. 2018. Shufflenet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, Salt Lake City, UT, USA, 6848–6856.

Cited By

Mai-Thanh LSon THuynh-The T(2024)Lite-GrSeg: Lightweight Architecture for 3D Point Cloud Road-Scene Semantic SegmentationComputational Intelligence Methods for Green Technology and Sustainable Development10.1007/978-3-031-76197-3_10(111-123)Online publication date: 24-Dec-2024
https://doi.org/10.1007/978-3-031-76197-3_10

Index Terms

Strategic Improvements of SqueezeSegV2 for Road-Scene Semantic Segmentation Using 3D LiDAR Point Cloud
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Image segmentation
  2. Machine learning
    1. Machine learning approaches
      1. Neural networks
2. Hardware
  1. Communication hardware, interfaces and storage
    1. Signal processing systems
      1. Digital signal processing

Recommendations

PointGANet: A Lightweight 3D Point Cloud Learning Architecture for Semantic Segmentation
SOICT '23: Proceedings of the 12th International Symposium on Information and Communication Technology

PointNet++ has gained significant acknowledgement for point cloud data processing capabilities. Over time, various network improvements have been developed to enhance its global learning efficiency, thus boosting the correct segmentation rate. However, ...
LiPoSeg: A Lightweight Encoder-Decoder Network for LiDAR-based Road-Object Semantic Segmentation
SOICT '23: Proceedings of the 12th International Symposium on Information and Communication Technology

LiDAR point cloud segmentation is one of the most challenging tasks in autonomous driving systems, as it requires a cutting-edge perception method that should be accurate, low-cost, and real-time. In the last decade, several deep encoder-decoder neural ...
Real-time road object segmentation using improved light-weight convolutional neural network based on 3D LiDAR point cloud

It is critical that autonomous navigation systems can segment the objects captured by their sensors (cameras or LiDAR scanners) in real-time. A convolutional neural networks (CNN) is proposed for real-time semantic segmentation of road objects (...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

SOICT '23: Proceedings of the 12th International Symposium on Information and Communication Technology

December 2023

1058 pages

ISBN:9798400708916

DOI:10.1145/3628797

Copyright © 2023 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 December 2023

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

SOICT 2023

SOICT 2023: The 12th International Symposium on Information and Communication Technology

December 7 - 8, 2023

Ho Chi Minh, Vietnam

Acceptance Rates

Overall Acceptance Rate 147 of 318 submissions, 46%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
56
Total Downloads

Downloads (Last 12 months)17
Downloads (Last 6 weeks)2

Reflects downloads up to 06 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Mai-Thanh LSon THuynh-The T(2024)Lite-GrSeg: Lightweight Architecture for 3D Point Cloud Road-Scene Semantic SegmentationComputational Intelligence Methods for Green Technology and Sustainable Development10.1007/978-3-031-76197-3_10(111-123)Online publication date: 24-Dec-2024
https://doi.org/10.1007/978-3-031-76197-3_10

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View Table of Conten