Action Recognition Based on Multi-Level Topological Channel Attention of Human Skeleton

被引:3
|
作者
Hu, Kai [1 ,2 ]
Shen, Chaowen [1 ]
Wang, Tianyan [1 ]
Shen, Shuai [1 ]
Cai, Chengxue [1 ]
Huang, Huaming [3 ]
Xia, Min [1 ,2 ]
机构
[1] Nanjing Univ Informat Sci & Technol, Sch Automat, Nanjing 210044, Peoples R China
[2] Nanjing Univ Informat Sci & Technol, CICAEET, Nanjing 210044, Peoples R China
[3] Nanjing Univ Informat Sci & Technol, Dept Phys Educ, Nanjing 210044, Peoples R China
基金
中国国家自然科学基金;
关键词
skeleton action recognition; temporal modeling; prior knowledge; ENSEMBLE; NETWORK;
D O I
10.3390/s23249738
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
In action recognition, obtaining skeleton data from human poses is valuable. This process can help eliminate negative effects of environmental noise, including changes in background and lighting conditions. Although GCN can learn unique action features, it fails to fully utilize the prior knowledge of human body structure and the coordination relations between limbs. To address these issues, this paper proposes a Multi-level Topological Channel Attention Network algorithm: Firstly, the Multi-level Topology and Channel Attention Module incorporates prior knowledge of human body structure using a coarse-to-fine approach, effectively extracting action features. Secondly, the Coordination Module utilizes contralateral and ipsilateral coordinated movements in human kinematics. Lastly, the Multi-scale Global Spatio-temporal Attention Module captures spatiotemporal features of different granularities and incorporates a causal convolution block and masked temporal attention to prevent non-causal relationships. This method achieved accuracy rates of 91.9% (Xsub), 96.3% (Xview), 88.5% (Xsub), and 90.3% (Xset) on NTU-RGB+D 60 and NTU-RGB+D 120, respectively.
引用
收藏
页数:26
相关论文
共 50 条
  • [21] Attention-based Multi-level Feature Fusion for Named Entity Recognition
    Yang, Zhiwei
    Chen, Hechang
    Zhang, Jiawei
    Ma, Jing
    Chang, Yi
    PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 3594 - 3600
  • [22] Remote Sensing Image Segmentation Method Based on Multi-Level Channel Attention
    Yu Shuai
    Wang Xili
    LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (04)
  • [23] Human Action Recognition Network Based on Improved Channel Attention Mechanism
    Chen Ying
    Gong Suming
    JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2021, 43 (12) : 3538 - 3545
  • [24] Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)
    Mehmood, Faisal
    Guo, Xin
    Chen, Enqing
    Akbar, Muhammad Azeem
    Khan, Arif Ali
    Ullah, Sami
    COMPUTERS IN HUMAN BEHAVIOR, 2025, 163
  • [25] Human Action Recognition Based on Skeleton Features
    Gao, Yi
    Wu, Haitao
    Wu, Xinmeng
    Li, Zilin
    Zhao, Xiaofan
    COMPUTER SCIENCE AND INFORMATION SYSTEMS, 2023, 20 (01) : 537 - 550
  • [26] Human action recognition based on skeleton splitting
    Yoon, Sang Min
    Kuijper, Arjan
    EXPERT SYSTEMS WITH APPLICATIONS, 2013, 40 (17) : 6848 - 6855
  • [27] Insight on Attention Modules for Skeleton-Based Action Recognition
    Jiang, Quanyan
    Wu, Xiaojun
    Kittler, Josef
    PATTERN RECOGNITION AND COMPUTER VISION, PT I, 2021, 13019 : 242 - 255
  • [28] Memory Attention Networks for Skeleton-based Action Recognition
    Xie, Chunyu
    Li, Ce
    Zhang, Baochang
    Chen, Chen
    Han, Jungong
    Liu, Jianzhuang
    PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2018, : 1639 - 1645
  • [29] ACTION RECOGNITION BASED ON MULTI-LEVEL REPRESENTATION OF 3D SHAPE
    Nair, Binu M.
    Asari, Vijayan K.
    VISAPP 2011: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, 2011, : 378 - 386
  • [30] Human Action Recognition Based on Skeleton Information and Multi-Feature Fusion
    Wang, Li
    Su, Bo
    Liu, Qunpo
    Gao, Ruxin
    Zhang, Jianjun
    Wang, Guodong
    ELECTRONICS, 2023, 12 (17)