Spatiotemporal Learning of Dynamic Gestures from 3D Point Cloud Data

被引:0
|
作者
Owoyemi, Joshua [1 ]
Hashimoto, Koichi [1 ]
机构
[1] Tohoku Univ, Grad Sch Informat Sci, Dept Syst Informat Sci, Aoba Ku, Sendai, Miyagi 9808579, Japan
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we demonstrate an end-to-end spatiotemporal gesture learning approach for 3D point cloud data using a new gestures dataset of point clouds acquired from a 3D sensor. Nine classes of gestures were learned from gestures sample data. We mapped point cloud data into dense occupancy grids, then time steps of the occupancy grids are used as inputs into a 3D convolutional neural network which learns the spatiotemporal features in the data without explicit modeling of gesture dynamics. We also introduced a 3D region of interest jittering approach for point cloud data augmentation. This resulted in an increased classification accuracy of up to 10% when the augmented data is added to the original training data. The developed model is able to classify gestures from the dataset with 84.44% accuracy. We propose that point cloud data will be a more viable data type for scene understanding and motion recognition, as 3D sensors become ubiquitous in years to come.
引用
收藏
页码:5929 / 5934
页数:6
相关论文
共 50 条
  • [1] Learning from 3D (Point Cloud) Data
    Hsu, Winston H.
    [J]. PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19), 2019, : 2697 - 2698
  • [2] Video coding of dynamic 3D point cloud data
    Schwarz, Sebastian
    Sheikhipour, Nahid
    Sevom, Vida Fakour
    Hannuksela, Miska M.
    [J]. APSIPA TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING, 2019, 8
  • [3] Faster Dynamic Graph CNN: Faster Deep Learning on 3D Point Cloud Data
    Hong, Jinseok
    Kim, Keeyoung
    Lee, Hongchul
    [J]. IEEE ACCESS, 2020, 8 : 190529 - 190538
  • [4] MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences
    Liu, Xingyu
    Yan, Mengyuan
    Bohg, Jeannette
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 9245 - 9254
  • [5] Feature extraction and representation learning of 3D point cloud data
    Si, Hongying
    Wei, Xianyong
    [J]. IMAGE AND VISION COMPUTING, 2024, 142
  • [6] Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis
    Liu, Fayao
    Lin, Guosheng
    Foo, Chuan-Sheng
    Joshi, Chaitanya K.
    Lin, Jie
    [J]. 2022 INTERNATIONAL CONFERENCE ON 3D VISION, 3DV, 2022, : 42 - 51
  • [7] Representing 3D Point Cloud Data
    Poux, Florent
    [J]. GIM INTERNATIONAL-THE WORLDWIDE MAGAZINE FOR GEOMATICS, 2022, 36 (04): : 36 - +
  • [8] Unsupervised contrastive learning with simple transformation for 3D point cloud data
    Jiang, Jincen
    Lu, Xuequan
    Ouyang, Wanli
    Wang, Meili
    [J]. VISUAL COMPUTER, 2024, 40 (08): : 5169 - 5186
  • [9] Learning to Estimate 3D Human Pose From Point Cloud
    Zhou, Yufan
    Dong, Haiwei
    Saddik, Abdulmotaleb El
    [J]. IEEE SENSORS JOURNAL, 2020, 20 (20) : 12334 - 12342
  • [10] Learning multiview 3D point cloud registration
    Gojcic, Zan
    Zhou, Caifa
    Wegner, Jan D.
    Guibas, Leonidas J.
    Birdal, Tolga
    [J]. 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 1756 - 1766