Action Recognition Based on the Fusion of Graph Convolutional Networks with High Order Features

Applied Sciences

HyoJong Lee¹  Jiuqing Dong²  Bo Huang²  Yongbin Gao²  Zhijun Fang²  Yifan Yao²  Heng Zhou² 

[1] Division of Computer Science and Engineering, CAIIT, Jeonbuk National University, Jeonju 54896, Korea;International Joint Research Lab of Intelligent Perception and Control, Shanghai University of Engineering Science, No. 333 Longteng Road, Shanghai 201620, China;

关键词: human action recognition;    graph convolution;    high-order feature;    spatio-temporal feature;    feature fusion;   

DOI  :  10.3390/app10041482

来源: DOAJ

【 摘 要 】

Skeleton-based action recognition is a widely used task in action related research because of its clear features and the invariance of human appearances and illumination. Furthermore, it can also effectively improve the robustness of the action recognition. Graph convolutional networks have been implemented on those skeletal data to recognize actions. Recent studies have shown that the graph convolutional neural network works well in the action recognition task using spatial and temporal features of skeleton data. The prevalent methods to extract the spatial and temporal features purely rely on a deep network to learn from primitive 3D position. In this paper, we propose a novel action recognition method applying high-order spatial and temporal features from skeleton data, such as velocity features, acceleration features, and relative distance between 3D joints. Meanwhile, a method of multi-stream feature fusion is adopted to fuse these high-order features we proposed. Extensive experiments on Two large and challenging datasets, NTU-RGBD and NTU-RGBD-120, indicate that our model achieves the state-of-the-art performance.

【 授权许可】

Unknown