Memory-boosting RNN with dynamic graph for event-based action recognition
Author:
Affiliation:

College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China

Clc Number:

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    Existing action recognition methods based on event cameras have not fully exploited the advantages of event cameras, such as compressing event streams into frames for subsequent calculation, which greatly sacrifices the time information of event streams. Meanwhile, the conventional PointCloud-based methods suffer from large computational complexity while processing event data, which make it difficult to handle long-term actions. To tackle the above problems, we propose a dynamic graph memory-boosting recurrent neural network (DG-MBRNN). The proposed DG-MBRNN splits the event stream into sequential graph data for preserving structural information, then uses the recurrent neural network (RNN) with boosting spatiotemporal memory to handle long-term sequences of actions. In addition, the proposed method introduces a dynamic reorganization mechanism for the graph based on the distances of features, which can effectively increase the ability to extract local features. In order to cope with the situation that the existing datasets have too simple actions and too limited categories, we propose a new event-based dataset containing 36 complex actions. This dataset will greatly promote the development of event-based action recognition research. Experimental results show the effectiveness of the proposed method in completing the event-based action recognition task.

    Reference
    Related
    Cited by
Get Citation

CHEN Guanzhou, LIU Sheng, XU Jingting. Memory-boosting RNN with dynamic graph for event-based action recognition[J]. Optoelectronics Letters,2023,19(10):629-634

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:February 20,2023
  • Revised:April 02,2023
  • Adopted:
  • Online: October 19,2023
  • Published: