3D Object Recognition with Ensemble Learning-A Study of Point Cloud-Based Deep Learning Models

被引:7
作者
Koguciuk, Daniel [1 ]
Chechlinski, Lukasz [1 ]
El-Gaaly, Tarek [2 ]
机构
[1] Warsaw Univ Technol, Fac Mech, Boboli 8, PL-05525 Warsaw, Poland
[2] Voyage, Palo Alto, CA USA
来源
ADVANCES IN VISUAL COMPUTING, ISVC 2019, PT II | 2019年 / 11845卷
关键词
Point cloud; Point set; Classification; Ensemble learning; 3D Deep Learning;
D O I
10.1007/978-3-030-33723-0_9
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this study, we present an analysis of model-based ensemble learning for 3D point-cloud object classification. An ensemble of multiple model instances is known to outperform a single model instance, but there is little study of the topic of ensemble learning for 3D point clouds. First, an ensemble of multiple model instances trained on the same part of the ModelNet40 dataset was tested for seven deep learning, point cloud-based classification algorithms: PointNet, PointNet++, SO-Net, KCNet, DeepSets, DGCNN, and PointCNN. Second, the ensemble of different architectures was tested. Results of our experiments show that the tested ensemble learning methods improve over state-of-the-art on the ModelNet40 dataset, from 92.65% to 93.64% for the ensemble of single architecture instances, 94.03% for two different architectures, and 94.15% for five different architectures. We show that the ensemble of two models with different architectures can be as effective as the ensemble of 10 models with the same architecture. Third, a study on classic bagging (i.e. with different subsets used for training multiple model instances) was tested and sources of ensemble accuracy growth were investigated for best-performing architecture, i.e. SO-Net. We measure the inference time of all 3D classification architectures on a Nvidia Jetson TX2, a common embedded computer for mobile robots, to allude to the use of these models in real-life applications.
引用
收藏
页码:100 / 114
页数:15
相关论文
共 50 条
  • [31] Hierarchical Edge Aware Learning for 3D Point Cloud
    Li, Lei
    ADVANCES IN COMPUTER GRAPHICS, CGI 2023, PT I, 2024, 14495 : 81 - 92
  • [32] Joint representation learning for text and 3D point cloud
    Huang, Rui
    Pan, Xuran
    Zheng, Henry
    Jiang, Haojun
    Xie, Zhifeng
    Wu, Cheng
    Song, Shiji
    Huang, Gao
    PATTERN RECOGNITION, 2024, 147
  • [33] Point Cloud-Based 3D Object Classification With Non Local Attention and Lightweight Convolution Neural Networks
    Karthik, R.
    Inamdar, Rohan
    Sundarr, S. Kavin
    Cho, Jaehyuk
    Veerappampalayam Easwaramoorthy, Sathishkumar
    IEEE ACCESS, 2024, 12 : 158530 - 158545
  • [34] 3D object recognition using deep learning for automatically generating semantic BIM data
    Rogage, Kay
    Doukari, Omar
    AUTOMATION IN CONSTRUCTION, 2024, 162
  • [35] Recent Advances and Perspectives in Deep Learning Techniques for 3D Point Cloud Data Processing
    Ding, Zifeng
    Sun, Yuxuan
    Xu, Sijin
    Pan, Yan
    Peng, Yanhong
    Mao, Zebing
    ROBOTICS, 2023, 12 (04)
  • [36] Deep Learning Approach to Point Cloud Scene Understanding for Automated Scan to 3D Reconstruction
    Chen, Jingdao
    Kira, Zsolt
    Cho, Yong K.
    JOURNAL OF COMPUTING IN CIVIL ENGINEERING, 2019, 33 (04)
  • [37] Modelling flood susceptibility based on deep learning coupling with ensemble learning models
    Li, Yuting
    Hong, Haoyuan
    JOURNAL OF ENVIRONMENTAL MANAGEMENT, 2023, 325
  • [38] Unbiased 3D Semantic Scene Graph Prediction in Point Cloud Using Deep Learning
    Han, Chaolin
    Li, Hongwei
    Xu, Jian
    Dong, Bing
    Wang, Yalin
    Zhou, Xiaowen
    Zhao, Shan
    APPLIED SCIENCES-BASEL, 2023, 13 (09):
  • [39] Advancing 3D point cloud understanding through deep transfer learning: A comprehensive survey
    Sohail, Shahab Saquib
    Himeur, Yassine
    Kheddar, Hamza
    Amira, Abbes
    Fadli, Fodil
    Atalla, Shadi
    Copiaco, Igail
    INFORMATION FUSION, 2025, 113
  • [40] A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation
    Sarker, Sushmita
    Sarker, Prithul
    Stone, Gunner
    Gorman, Ryan
    Tavakkoli, Alireza
    Bebis, George
    Sattarvand, Javad
    MACHINE VISION AND APPLICATIONS, 2024, 35 (04)