Human skeleton behavior recognition method, system, and device based on graph convolutional network

Abstract

The invention belongs to the field of computer vision and deep learning, and specifically relates to a human skeleton behavior recognition method, system, and device based on a graph convolutional network, aiming to solve the problem that the accuracy of human skeleton behavior recognition results based on a graph convolutional neural network is not high question. The method of the present invention includes: obtaining the skeleton video frame and normalizing it; constructing a natural connection diagram of human body joints corresponding to each frame diagram; learning unnatural connection edges to obtain a human body joint connection diagram; assigning weight values ​​to each edge of the human body joint connection diagram ; Perform graph convolution operation to obtain the spatial information of the skeleton sequence; perform convolution operation on the time dimension to obtain the behavior category of the skeleton sequence. The natural connection edge of the present invention can learn the basic human behavior characteristics, and at the same time, the unnatural connection edge can learn additional behavior characteristics, and the natural connection edge and the unnatural connection edge together form a graph, which can more fully represent the human body movement information , to improve recognition performance.

Description

technical field [0001] The invention belongs to the field of computer vision and deep learning, and in particular relates to a human skeleton behavior recognition method, system and device based on a graph convolutional network. Background technique [0002] As an important research field of computer vision, behavior recognition aims to distinguish the category of human behavior from a given video. Behavior recognition is widely used and has important research value in many fields such as smart home, motion analysis, video surveillance, and human-computer interaction. The current behavior recognition methods are mainly researched from two perspectives based on RGB video and based on human skeleton joints. The method based on RGB video is easily affected by illumination and occlusion, and has poor robustness, while the method based on human bone joint points is extremely discriminative, unaffected by illumination, and relatively sensitive to viewing angle transformation and ...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned problems in the prior art, that is, the problem that the accuracy of human skeleton behavior recognition results based on graph convolutional neural network is not high, the present invention provides a human skeleton behavior recognition method based on graph convolutional network, including:

Images