Recognition and Segmentation of 3D Point Clouds Sensitive to Fusion Features

ZHU Andi; DA Feipeng; GAI Shaoyan

doi:10.7652/xjtuxb202405006

您当前的位置：

首页 >

文章列表页 >

Recognition and Segmentation of 3D Point Clouds Sensitive to Fusion Features

更新时间：2025-07-28

- Recognition and Segmentation of 3D Point Clouds Sensitive to Fusion Features
- Vol. 58, Issue 5, Pages: 52-63(2024)
- 作者机构：
  
  1. 东南大学自动化学院,南京,210096
  2. 东南大学复杂工程系统测量与控制教育部重点实验室,南京,210096
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202405006
  CLC： TP391
- Online First：10 May 2024，
  
  Published：2024
- 稿件说明：
移动端阅览
ZHU Andi, DA Feipeng, GAI Shaoyan. Recognition and Segmentation of 3D Point Clouds Sensitive to Fusion Features[J]. 2024, 58(5): 52-63.
DOI：

ZHU Andi, DA Feipeng, GAI Shaoyan. Recognition and Segmentation of 3D Point Clouds Sensitive to Fusion Features[J]. 2024, 58(5): 52-63. DOI： 10.7652/xjtuxb202405006.

摘要

三维点云分类分割网络忽视了融合特征中的冗余信息

缺乏放大有效特征占比能力

不能充分挖掘特征的表达性。在CurveNet网络基础上

提出了一种能够筛选和丰富融合特征的方法

对点云的识别与分割效果达到了较先进水平。首先

提出了对融合特征具有筛选能力的特征选择子网络

利用结合了打分机制的TopK算子选出包含有效信息的融合特征

并且能够自适应地赋予被选特征权重。其次

在聚合曲线特征模块中增加了两个新分支

分别学习曲线内部点距离特征和曲线之间的线距离特征

通过快速通道相关性注意力机制提取各分支的内部相关性

增强了网络特征的信息描述能力。实验结果表明

分类任务在ModelNet40数据集上准确率达到了93.8%

分割任务在ShapeNet Part数据集上平均交并比达到了86.4%。与基准网络相比

分类效果与分割效果均有所提高

证明了算法的有效性。

Abstract

The 3D point cloud classification and segmentation networks ignore the redundant information in the fusion features

lack the ability to amplify the proportion of effective features

and cannot fully explore the expressiveness of features. Based on the CurveNet network

this paper proposes a method that can filter and enrich the fusion features

and the recognition and segmentation effect of point cloud reaches a relatively advanced level. Firstly

a feature selection subnetwork with filtering ability for fusion features is proposed

which combines TopK operator and a scoring mechanism to select fusion features containing valid information and adaptively assign weight to the selected features. Secondly

two new branches are added to the aggregation curve feature module

so as to learn the curve internal point distance features and the curve line distance features

respectively

and extract the internal correlation of each branch through the quick channel affinity attention mechanism

which enhances the information description ability of the network features. The experimental results show that the accuracy of the classification task on the ModelNet40 dataset reaches 93.8%

and the average intersection over union of the segmentation task on the ShapeNet Part dataset reaches 86.4%. Compared with the benchmark network

the classification effect and segmentation effect are improved

which proves the effectiveness of the proposed algorithm.

关键词

Keywords

references

CHARLES R Q, SU Hao, KAICHUN M, et al. PointNet: deep learning on point sets for 3D classification and segmentation [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2017: 77-85.

QI C R, YI Li, SU Hao, et al. PointNet++: deep hierarchical feature learning on point sets in a metric space [C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY, USA: Curran Associates Inc., 2017: 5105-5114.

JIANG Mingyang, WU Yiran, ZHAO Tianqi, et al. PointSIFT: a SIFT-like network module for 3D point cloud semantic segmentation [EB/OL].(2018-11-24)[2023-08-10]. https://arxiv.org/abs/1807.00652.

JOSEPH-RIVLIN M, ZVIRIN A, KIMMEL R. Momen(e)t: flavor the moments in learning to classify shapes [C]//2019 IEEE/CVF International Conference on Computer Vision Workshop(ICCVW). Piscataway, NJ, USA: IEEE, 2019: 4085-4094.

ZHAO Hengshuang, JIANG Li, FU C W, et al. PointWeb: enhancing local neighborhood features for point cloud processing [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2019: 5560-5568.

王溪波, 曹士彭, 赵怀慈, 等. 双边特征聚合与注意力机制点云语义分割 [J]. 仪器仪表学报, 2021, 42(12): 175-183.

WANG Xibo, CAO Shipeng, ZHAO Huaici, et al. Semantic segmentation of point cloud via bilateral feature aggregation and attention mechanism [J]. Chinese Journal of Scientific Instrument, 2021, 42(12): 175-183.

KOMARICHEV A, ZHONG Zichun, HUA Jing. A-CNN: annularly convolutional neural networks on point clouds [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2019: 7413-7422.

LI Yangyan, BU Rui, SUN Mingchao, et al. PointCNN: convolution on X-transformed points [C]//Advances in Neural Information Processing Systems. San Francisco, CA, USA: Curran Associates Inc., 2018: 820-830.

LIU Yongcheng, FAN Bin, XIANG Shiming, et al. Relation-shape convolutional neural network for point cloud analysis [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2019: 8887-8896.

WU Wenxuan, QI Zhongang, FUXIN Li. PointConv: deep convolutional networks on 3D point clouds [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2019: 9613-9622.

THOMAS H, QI C R, DESCHAUD J E, et al. KPConv: flexible and deformable convolution for point clouds [C]//2019 IEEE/CVF International Conference on Computer Vision(ICCV). Piscataway, NJ, USA: IEEE, 2019: 6410-6419.

彭秀平, 仝其胜, 林洪彬, 等. 一种面向散乱点云语义分割的深度残差-特征金字塔网络框架 [J]. 自动化学报, 2021, 47(12): 2831-2840.

PENG Xiuping, TONG Qisheng, LIN Hongbin, et al. A deep residual-feature pyramid network framework for scattered point cloud semantic segmentation [J]. Acta Automatica Sinica, 2021, 47(12): 2831-2840.

WANG Yue, SUN Yongbin, LIU Ziwei, et al. Dynamic graph CNN for learning on point clouds [J]. ACM Transactions on Graphics, 2019, 38(5): 146.

LANDRIEU L, SIMONOVSKY M. Large-scale point cloud semantic segmentation with superpoint graphs [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 4558-4567.

WANG Lei, HUANG Yuchun, HOU Yaolin, et al. Graph attention convolution for point cloud semantic segmentation [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2019: 10288-10297.

李冠彬, 张锐斐, 陈超, 等. 基于旋转不变深度层次聚类网络的点云分析 [J]. 软件学报, 2022, 33(11): 4356-4378.

LI Guanbin, ZHANG Ruifei, CHEN Chao, et al. Rotation-invariant deep hierarchical cluster network for point cloud analysis [J]. Journal of Software, 2022, 33(11): 4356-4378.

MA Xu, QIN Can, YOU Haoxuan, et al. Rethinking network design and local geometry in point cloud: a simple residual MLP framework [J/OL].(2022-11-29)[2023-08-22]. https://arxiv.org/abs/2202.07123.

杨军, 王连甲. 结合位置关系卷积与深度残差网络的三维点云识别与分割 [J]. 西安交通大学学报, 2023, 57(5): 182-193.

YANG Jun, WANG Lianjia. Recognition and segmentation of 3D point cloud through positional relation convolution in combination with deep residual network [J]. Journal of Xi'an Jiaotong University, 2023, 57(5): 182-193.

XIANG Tiange, ZHANG Chaoyi, SONG Yang, et al. Walk in the cloud: learning curves for point clouds shape analysis [C]//2021 IEEE/CVF International Conference on Computer Vision(ICCV). Piscataway, NJ, USA: IEEE, 2021: 895-904.

WU Bingli, MA Jie, CHEN Gaojie, et al. Feature interactive representation for point cloud registration [C]//2021 IEEE/CVF International Conference on Computer Vision(ICCV). Piscataway, NJ, USA: IEEE, 2021: 5510-5519.

QIU Shi, ANWAR S, BARNES N. Geometric back-projection network for point cloud classification [J]. IEEE Transactions on Multimedia, 2022, 24: 1943-1955.

WAZIR S, FRAZ M M. HistoSeg: quick attention with multi-loss function for multi-structure segmentation in digital histology images [C]//2022 12th International Conference on Pattern Recognition Systems(ICPRS). Piscataway, NJ, USA: IEEE, 2022: 1-7.

YAN Xu, ZHENG Chaoda, LI Zhen, et al. Point ASNL: robust point clouds processing using nonlocal neural networks with adaptive sampling [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2020: 5588-5597.

XU Mutian, DING Runyu, ZHAO Hengshuang, et al. PAConv: position adaptive convolution with dynamic kernel assembling on point clouds [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2021: 3172-3181.

GUO Menghao, CAI Junxiong, LIU Zhengning, et al. PCT: point cloud transformer [J]. Computational Visual Media, 2021, 7(2): 187-199.[26] LI Jiaxin, CHEN Benm, LEE G H. SO-Net: self-organizing network for point cloud analysis [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 9397-9406.

YU Xumin, TANG Lulu, RAO Yongming, et al. Point-BERT: pre-training 3D point cloud transformers with masked point modeling [C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2022: 19291-19300.

ZHANG Renrui, WANG Liuhui, GUO Ziyu, et al. Parameter is not all you need: starting from non-parametric networks for 3D point cloud analysis [EB/OL].(2021-05-10)[2023-08-22]. https://arxiv.org/abs/2303.08134.

YAN S, YANG Z, LI H, et al. Implicit autoencoder for point-cloud self-supervised representation learning [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. [S.l.]: [s.n.], 2023: 14530-14542.

ZHANG Renrui, WANG Liuhui, QIAO Yu, et al. Learning 3D representations from 2D pre-trained models via image-to-point masked autoencoders [C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2023: 21769-21780.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

I/O Performance Modeling and Prediction Method for Large-Scale Parallel Applications Using Machine Learning

Effects of Steam Addition on the Swirl Combustion and Emission Characteristics of Cracked Ammonia

A Fast Calculation Method for Thermal Flow Fields in Transformer Windings Based on PI-DeepONet

Bi-Level Multi-Obj ective Optimization of a Wind-Solar Coupled Hydrogen Production System Based on the Synergy of Hybrid Electrolyzer Arrays

Review of the Application of EBSILON Software in Combined Heat and Power System Optimization

Related Author

No data

Related Institution

No data

⁰