WANG Shihui, ZHU Yongxin, WANG Hui, ZHENG Xiaoying. Multi-modal group activity recognition method combining motion trajectory features[J]. Microelectronics & Computer, 2021, 38(11): 7-13. DOI: 10.19304/J.ISSN1000-7180.2021.0341
Citation: WANG Shihui, ZHU Yongxin, WANG Hui, ZHENG Xiaoying. Multi-modal group activity recognition method combining motion trajectory features[J]. Microelectronics & Computer, 2021, 38(11): 7-13. DOI: 10.19304/J.ISSN1000-7180.2021.0341

Multi-modal group activity recognition method combining motion trajectory features

  • Group Activity Recognition focused on group activities and individual actions classification from a group level perspective. A better group activity recognition result is of great significance to applications such as security monitoring and sports video analysis. To deal with the problem that current LSTM based models could not fully extract spatial-temporal features at group level, a LSTM-Transformer based group activity recognition model was proposed to utilize group-individual features. Additionally, a multi-modal model combining trajectory features was proposed for the first time at group activity recognition.The experimental results show that compared with the existing LSTM-based models, the accuracy of the proposed model's group activity recognition is increased by 8.3%, and the accuracy of individual action recognition is increased by 2.1%. Compared with the GCN-based model, the proposed model not only improves the recognition accuracy, but also can handle group with varying size.
  • loading

Catalog

    Turn off MathJax
    Article Contents

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return