Non-local Graph Convolutional Network for joint Activity Recognition and Motion Prediction

被引:6
作者
Zhang, Dianhao [1 ]
Ngo Anh Vien [2 ]
Mien Van [1 ]
McLoone, Sean [1 ]
机构
[1] Queens Univ Belfast, Belfast, Antrim, North Ireland
[2] Bosch Ctr Artificial Intelligence, Renningen, Germany
来源
2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) | 2021年
关键词
LSTM; Graph Convolutional Network; Motion Prediction; Action Recognition; Human-robot Collaboration;
D O I
10.1109/IROS51168.2021.9636107
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
3D skeleton-based motion prediction and activity recognition are two interwoven tasks in human behaviour analysis. In this work, we propose a motion context modeling methodology that provides a new way to combine the advantages of both graph convolutional neural networks and recurrent neural networks for joint human motion prediction and activity recognition. Our approach is based on using an LSTM encoder-decoder and a non-local feature extraction attention mechanism to model the spatial correlation of human skeleton data and temporal correlation among motion frames. The proposed network can easily include two output branches, one for Activity Recognition and one for Future Motion Prediction, which can be jointly trained for enhanced performance. Experimental results on Human 3.6M, CMU Mocap and NTU RGB-D datasets show that our proposed approach provides the best prediction capability among baseline LSTM-based methods, while achieving comparable performance to other state-of-the-art methods.
引用
收藏
页码:2970 / 2977
页数:8
相关论文
共 43 条
  • [1] Aksan Emre, 2020, ARXIV E PRINTS
  • [2] [Anonymous], 2016, Ntu rgb+d: A large scale dataset for 3d human activity analysis
  • [3] [Anonymous], 2015, Advances in Neural Information Processing Systems, DOI DOI 10.5555/2969239.2969370
  • [4] Bahdanau D, 2016, Arxiv, DOI arXiv:1409.0473
  • [5] Action-Agnostic Human Pose Forecasting
    Chiu, Hsu-kuang
    Adeli, Ehsan
    Wang, Borui
    Huang, De-An
    Niebles, Juan Carlos
    [J]. 2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2019, : 1423 - 1432
  • [6] Action Recognition Based on the Fusion of Graph Convolutional Networks with High Order Features
    Dong, Jiuqing
    Gao, Yongbin
    Lee, Hyo Jong
    Zhou, Heng
    Yao, Yifan
    Fang, Zhijun
    Huang, Bo
    [J]. APPLIED SCIENCES-BASEL, 2020, 10 (04):
  • [7] Du Y, 2015, PROC CVPR IEEE, P1110, DOI 10.1109/CVPR.2015.7298714
  • [8] Fraccaro Marco, 2017, DISENTANGLED RECOGNI, P10
  • [9] Recurrent Network Models for Human Dynamics
    Fragkiadaki, Katerina
    Levine, Sergey
    Felsen, Panna
    Malik, Jitendra
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 4346 - 4354
  • [10] Gao Xiang, 2019, OPTIMIZED SKELETON B