Skeleton Motion Recognition Based on Multi-Scale Deep Spatio-Temporal Features

In the task of human motion recognition, the overall action span is changeable, and there may be an inclusion relationship between action semantics. This paper proposes a novel multi-scale time sampling module and a deep spatiotemporal feature extraction module, which strengthens the receptive field of the feature map and strengthens the extraction of spatiotemporal-related feature information via the network. We study and compare the performance of three existing multi-channel fusion methods to improve the recognition accuracy of the network on the open skeleton recognition dataset. In this paper, several groups of comparative experiments are carried out on two public datasets. The experimental results show that compared with the classical 2s-AGCN algorithm, the accuracy of the algorithm proposed in this paper shows an improvement of 1% on the Kinetics dataset and 0.4% and 1% on the two evaluating indicators of the NTU-RGB+D dataset, respectively.

Automated summary

This paper proposes a novel multi-scale time sampling module and a deep spatiotemporal feature extraction module to enhance the accuracy of human motion recognition network. Comparative experiments show that the proposed method achieves performance improvement on two datasets.