SKELETON ACTION RECOGNITION BASED ON SPATIO-TEMPORAL FEATURES

Graph convolutional network have performed well in action recognition tasks using skeleton data, but topology extraction remains a challenge. Most methods fail to consider the correlations between channels in skeleton topology graphs. To address this, we propose a multi-channel optimal graph convolutional network (MOGCN) that combines multi-channel optimal graph convolution and multi-scale temporal convolution techniques.MOGCN exhibits improved capability in processing spatiotemporal information and node relationships, generating optimal skeleton topology graphs that model correlations between all nodes in the sequence. We also use multi-scale temporal convolution to extract temporal features, improving the modeling of long-term correlations and global correlations of spatiotemporal joints. We further improve accuracy using a multi-stream fusion network model. Our experiments on multiple datasets show that our proposed MOGCN module is effective and improves the classification accuracy of action recognition tasks using skeleton data.