Double-person interaction identification method based on knowledge embedded graph convolutional network

Abstract

The invention discloses a double-person interaction identification method based on a knowledge embedded graph convolutional network, and mainly solves the problems that in the prior art, double-personassociation is neglected, double-person interaction characteristics cannot be extracted, and the double-person interaction identification accuracy is poor. According to the implementation scheme, themethod comprises the following steps: 1) designing a knowledge given graph to establish direct connection between skeleton points of two interactive persons; 2) designing a knowledge learning graph,and adaptively establishing connection between skeleton points; 3) constructing knowledge embedding graph convolution blocks capable of utilizing complementarity among different graphs; 4) sequentially connecting 10 knowledge embedded graph convolution blocks, a global pooling layer and a full connection layer to form a knowledge embedded graph convolution network; according to the double-person interaction behavior recognition method based on the knowledge embedding graph convolutional network, the accuracy of double-person interaction behavior recognition is improved, and the double-person interaction behavior recognition method based on the knowledge embedding graph convolutional network can be used for video retrieval, man-machine interaction and video understanding.

Description

technical field [0001] The invention belongs to the technical field of video processing, and further relates to a two-person interactive recognition method, which can be used for video retrieval, human-computer interaction and video understanding. Background technique [0002] Two-person interaction recognition can utilize many different modalities, such as red-green-blue color mode image RGB, depth and skeleton. Compared with the RGB and depth modes, the skeleton mode has the characteristics of less storage capacity and strong robustness to changes in environmental factors, and the skeleton data is a high abstraction of human characteristics, which can be well suited for two-person interaction identify. The current two-person behavior recognition methods for skeletal modalities are mainly based on recurrent neural networks, convolutional neural networks, and graph convolutional networks. Based on the method of recurrent neural network and convolutional neural network, the...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a two-person interaction recognition method based on knowledge-embedded graph convolutional network, to solve the existing method of constructing a skeleton graph according to the natural connection of the human body, ignoring the correlation of the skeleton points between the two interacting people, which cannot be guaranteed Suitable for all two-person interactive behaviors, and the problem of poor recognition effect

Images