Human motion identification method based on Gaussian process latent variable model

Abstract

The invention provides a discriminant human motion identification method based on a Gaussian process latent variable model and a hidden condition random field. The method mainly comprises that skeletal structure and motion information of the human body are obtained via motion capturing technology or Kinect motion sensing technology when motion data is obtained; when motion characteristics are extracted, the Gaussian process latent variable model added with a dynamic process and sparse approximation is used to obtain structure of high-dimension motion information in low-dimension hidden space and further to represent the motion characteristic; and when the human motion is identified, the discriminant hidden condition random field is used to model characteristics of sequential motion data, and motions are classified. According to the invention, characteristics of the human motions can be visualized, information among the sequential motion data can be used effectively, the human motions can be identified in high precision, and the method is suitable for the field of real-time human motion identification.

Description

technical field [0001] The invention belongs to the field of motion recognition, in particular to a discriminant recognition method based on a human body motion model of a Gaussian process hidden variable model and a hidden conditional random field. Background technique [0002] In the past two decades, human action recognition has become a hot research topic in the fields of computer vision, artificial intelligence, and pattern recognition. People hope that computers can think and understand some signals like the human brain, such as understanding our daily activities, so that computers can interact more naturally with humans. Its goal is to analyze the movements performed by the human body from an unknown image sequence. Recently, human action recognition has been widely used in video monitoring, human-computer interaction, medical care, intelligent security, virtual reality and other fields, and its research has important practical value and significance. [0003] Human...

AI Technical Summary

Problems solved by technology

In terms of feature extraction, it is easily affected by factors such as occlusion, viewing angle, lighting, dynamic background, and camera movement; in terms of classifier design, the algorithm research for time series data processing is still not deep enough to overcome the data independence and universality. and other stringent requirements

At present, a large number of researches focus on human action recognition based on video, and feature extraction is mostly an image processing process, while ignoring the important role of the chain bone structure of the human body in the recognition process.

Images