Graph convolutional neural network action recognition method based on attention mechanism

Abstract

The invention discloses a graph convolutional neural network action recognition method based on an attention mechanism, and relates to the field of human-computer interaction action recognition. The method comprises the steps of labelling N attention joints with the highest motion completion participation degree by a residual attention network, N can be 16, and setting other numerical values according to the actual situation; constructing a three-dimensional skeleton space-time diagram, and carrying out space-time feature coding on the attention joints; and learning the three-dimensional skeleton space-time graph through a graph convolutional neural network GCN to perform action recognition. The joints with high participation degree for completing the specific action are selected based on the residual attention network, so that the information processing redundancy can be reduced, and joint information which does not contribute to action recognition is abandoned; based on space-time constraints between the joints, space-time feature codes about the attention joints are constructed to more effectively represent space-time features of the attention joints; based on human body space structure natural graph representation, a graph convolutional neural network is utilized to obtain depth representation about a three-dimensional skeleton space-time graph so as to effectively recognize actions.

Description

technical field [0001] The invention relates to the field of human-computer interaction action recognition, in particular to an attention mechanism-based graph convolutional neural network action recognition method. Background technique [0002] As one of the important ways of non-contact interaction to replace traditional contact human-computer interaction methods such as keyboards, buttons, and touch screens, vision-based action recognition has become a research hotspot in the field of computer vision. Although people have studied vision-based action recognition for many years, it is still unable to be applied on a large scale, mainly facing the following technical difficulties: factors such as illumination changes and cluttered backgrounds make the action recognition method less robust; depth image information redundancy The large degree increases the computational complexity of the algorithm, which in turn limits the application of action recognition methods; the origina...

AI Technical Summary

Problems solved by technology

Tang et al. proposed a deep progressive reinforcement learning (DPRL) method to select more informative frames in the input sequence, and used GCN to learn the inter-joint dependencies, but it ignored the bone time information

Bin et al. proposed a spatiotemporal graph trajectory (STGR) method to study bone-based action recognition. This method learns spatiotemporal continuity, but its graph learning has high computational complexity, and the spatial graph is built on clusters, and each cluster is Only has a single weight, so it cannot capture the subtle spatial relationship between nodes

Images