A novel posture motion-based spatiotemporal fused graph convolutional network (PM-STGCN) is presented for skeleton-based\naction recognition. Existing methods on skeleton-based action recognition focus on independently calculating the joint information\nin single frame and motion information of joints between adjacent frames from the human body skeleton structure and\nthen combine the classification results. However, that does not take into consideration of the complicated temporal and spatial\nrelationship of the human body action sequence, so they are not very efficient in distinguishing similar actions. In this work, we\nenhance the ability of distinguishing similar actions by focusing on spatiotemporal fusion and adaptive feature extraction for high\ndiscrimination information. Firstly, the local posture motion-based attention (LPM-TAM) module is proposed for the purpose of\nsuppressing the skeleton sequence data with a low amount of motion in the temporal domain, and the representation of motion\nposture features is concentrated. Besides, the local posture motion-based channel attention module (LPM-CAM) is introduced to\nmake use of the strongly discriminative representation between different action classes of similarity. Finally, the posture motionbased\nspatiotemporal fusion (PM-STF) module is constructed which fuses the spatiotemporal skeleton data by filtering out the\nlow-information sequence and enhances the posture motion features adaptively with high discrimination. Extensive experiments\nhave been conducted, and the results demonstrate that the proposed model is superior to the commonly used action recognition\nmethods. The designed human-robot interaction system based on action recognition has competitive performance compared with\nthe speech interaction system.
Loading....