Behavior recognition method, system and device based on human skeleton and medium

Abstract

The invention discloses a behavior recognition method, system and device based on a human skeleton and a medium. The method comprises the following steps: acquiring spatio-temporal sequence data of ahuman skeleton; inputting the space-time sequence data into a behavior recognition model to obtain a behavior recognition result; wherein the behavior recognition model comprises a first processing unit, a class activation mapping unit, a second processing unit and a classification unit; wherein the first processing unit is connected to the second processing unit through the class activation mapping unit, and the first processing unit and the second processing unit are connected to the classification unit. According to the recognition method provided by the embodiment of the invention, the twodata streams are processed through the first processing unit and the second processing unit, and richer and more discriminative features can be extracted for behavior recognition, so that behaviors and actions of a human body can be recognized more accurately and effectively, and the recognition accuracy is improved. The method can be widely applied to the technical field of computer vision.

Description

technical field [0001] The present application relates to the field of computer vision technology, especially a method, system, device and medium for behavior recognition based on human skeleton. Background technique [0002] Currently, action recognition based on 3D human skeleton is one of the most active research fields in computer vision. Behavior recognition has a very wide range of applications, such as human-computer interaction, intelligent surveillance systems, virtual reality, sports, and healthcare, among others, and these applications are one of the motivations for a large number of research efforts devoted to this field. In this field, previous research on action recognition has focused on methods dominated by traditional RGB videos, which still have relatively low recognition accuracy even when the scene is free of clutter. While traditional human skeleton-based behavior recognition methods mainly focus on designing handcrafted features representing the skelet...

AI Technical Summary

Problems solved by technology

For example, in the spatio-temporal graph convolutional network model (ST-GCN), the graph construction process has at least the following disadvantages: (1) The skeleton graph used in ST-GCN is predefined, and this only represents the physical structure of the human body

However, the topology of graphs applied to GCNs is fixed on all layers, which lacks the flexibility and ability to model multi-level semantic information contained in all layers; (3) a fixed graph structure for different All samples of the action class may not be optimal

Images