高级检索

    付仔蓉, 吴胜昔, 吴潇颖, 顾幸生. 基于空间特征的BI-LSTM人体行为识别[J]. 华东理工大学学报(自然科学版), 2021, 47(2): 225-232. DOI: 10.14135/j.cnki.1006-3080.20191202003
    引用本文: 付仔蓉, 吴胜昔, 吴潇颖, 顾幸生. 基于空间特征的BI-LSTM人体行为识别[J]. 华东理工大学学报(自然科学版), 2021, 47(2): 225-232. DOI: 10.14135/j.cnki.1006-3080.20191202003
    FU Zirong, WU Shengxi, WU Xiaoying, GU Xingsheng. Human Action Recognition Using BI-LSTM Network Based on Spatial Features[J]. Journal of East China University of Science and Technology, 2021, 47(2): 225-232. DOI: 10.14135/j.cnki.1006-3080.20191202003
    Citation: FU Zirong, WU Shengxi, WU Xiaoying, GU Xingsheng. Human Action Recognition Using BI-LSTM Network Based on Spatial Features[J]. Journal of East China University of Science and Technology, 2021, 47(2): 225-232. DOI: 10.14135/j.cnki.1006-3080.20191202003

    基于空间特征的BI-LSTM人体行为识别

    Human Action Recognition Using BI-LSTM Network Based on Spatial Features

    • 摘要: 随着微软Kinect等深度相机的出现,使用具有简洁性、鲁棒性和视图无关表示的3D骨架节点数据来识别人体行为的方法获得了很好的效果,但现有的针对骨骼序列数据的大多数学习方法缺少空间结构信息和详细的时空动态信息。利用双向长短期记忆网络(BI-LSTM)模型能长时间存储骨骼序列的特点获得丰富的双向时间信息对动作的顺序进行建模,同时从3D骨骼关节点坐标中提取关节点之间的相对距离特征和相对角度特征来加强空间结构特征,完成从骨骼数据中实现人体行为识别。该方法有效地进行了人体行为动作分类,提高了识别准确性。

       

      Abstract: With the advent of depth cameras such as microsoft Kinect, the method of recognizing human action via 3D skeleton node data with simplicity, robustness and view-independent representation has achieved quite good performance. However, most of the existing methods for skeleton sequence data lack spatial structure information and detailed temporal dynamics features. By means of the characteristics of BI-LSTM model with the long-term storage of skeleton sequences, rich bidirectional time information to model the sequence of actions is obtained. Meanwhile, the relative distance features and relative angle features between joint points are extracted from 3D bone joint point coordinates to strengthen the spatial structure features and realize the recognition of human action from the skeleton data. Finally, it is shown via the simulation results that this proposed method can effectively achieve the classification of human actions and improve the accuracy.

       

    /

    返回文章
    返回