RFNet: Convolutional Neural Network for 3D Point Cloud Classification

被引:0
|
作者
Shan, Xuan-Yang [1 ]
Sun, Zhan-Li [2 ]
Zeng, Zhi-Gang [3 ]
机构
[1] School of Electrical Engineering and Automation, Anhui University, Hefei,230601, China
[2] School of Artificial Intelligence, Anhui University, Hefei,230601, China
[3] School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan,430000, China
来源
基金
中国国家自然科学基金;
关键词
D O I
10.16383/j.aas.c210532
中图分类号
TB18 [人体工程学]; Q98 [人类学];
学科分类号
030303 ; 1201 ;
摘要
Due to the unstructured and disordered nature of point cloud, the classification accuracy is still needed to improve for the currently existed point cloud classification approaches. In this paper, an effective point cloud classification network is proposed by considering local structure construction, global feature aggregation, and loss function improvement. Firstly, in view of the unstructured nature of point cloud, the local structure is constructed via assigning different weights to those irregular neighborhood points, which are computed via the relationship between the center point feature and its neighbor feature. Moreover, a strategy of weighted average pooling (WAP) is designed to learn the attention score of each high-dimensional feature through self-attention mechanization, which can effectively aggregate redundant high-dimensional features while coping with point cloud disorder. In addition, a joint loss function (JL) is presented by utilizing the complementary relationship between the cross-entropy loss and the center loss, which increases the inter-class distance while reduces the intro-class distance, and further improves the classification ability of the network. Compared to several state-of-the-art networks, the experimental results on the synthetic dataset ModelNet40 and ShapeNetCore and the real-world dataset ScanObjectNN demonstrate the superiority of the overall network structure. © 2023 Science Press. All rights reserved.
引用
收藏
页码:2350 / 2359
相关论文
共 50 条
  • [1] Fusion of a Static and Dynamic Convolutional Neural Network for Multiview 3D Point Cloud Classification
    Wang, Wenju
    Zhou, Haoran
    Chen, Gang
    Wang, Xiaolin
    [J]. REMOTE SENSING, 2022, 14 (09)
  • [2] Point Cloud Labeling using 3D Convolutional Neural Network
    Huang, Jing
    You, Suya
    [J]. 2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, : 2670 - 2675
  • [3] Convolutional neural networks with hybrid weights for 3D point cloud classification
    Meng Hu
    Hailiang Ye
    Feilong Cao
    [J]. Applied Intelligence, 2021, 51 : 6983 - 6996
  • [4] Convolutional neural networks with hybrid weights for 3D point cloud classification
    Hu, Meng
    Ye, Hailiang
    Cao, Feilong
    [J]. APPLIED INTELLIGENCE, 2021, 51 (10) : 6983 - 6996
  • [5] Convolutional Neural Network for 3D Point Cloud Quality Assessment with Reference
    Chetouani, Aladine
    Quach, Maurice
    Valenzise, Giuseppe
    Dufaux, Frederic
    [J]. IEEE MMSP 2021: 2021 IEEE 23RD INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP), 2021,
  • [6] An Optimized Convolutional Neural Network for the 3D Point-Cloud Compression
    Luo, Guoliang
    He, Bingqin
    Xiong, Yanbo
    Wang, Luqi
    Wang, Hui
    Zhu, Zhiliang
    Shi, Xiangren
    [J]. SENSORS, 2023, 23 (04)
  • [7] 3D Point Cloud Classification and Segmentation Model Based on Graph Convolutional Network
    Hou Xiangdan
    Yu Xixin
    Liu Hongpu
    [J]. LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (18)
  • [8] A Graphical Convolutional Network-based Method for 3D Point Cloud Classification
    Wang, Liang
    Li, Jianshu
    Pan, Deqiao
    [J]. PROCEEDINGS OF THE 33RD CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2021), 2021, : 1686 - 1691
  • [9] Design of neural network model for lightweight 3D point cloud classification
    Wang, Chenxia
    Shi, Taibin
    Tang, Linlin
    Chen, Yeh-Cheng
    [J]. Journal of Network Intelligence, 2020, 5 (03): : 122 - 128
  • [10] Point cloud based deep convolutional neural network for 3D face recognition
    Anagha R. Bhople
    Akhilesh M. Shrivastava
    Surya Prakash
    [J]. Multimedia Tools and Applications, 2021, 80 : 30237 - 30259