Human body posture motion capture algorithm based on heterogeneous data fusion

Abstract

The invention discloses a human body posture motion capture algorithm based on heterogeneous data fusion. The algorithm comprises the following steps: (1) acquiring human body motion data by using a plurality of sensor node posture acquisition modules fixed at various feature parts of the human body, each sensor node comprising a three-axis accelerometer, a three-axis gyroscope and a three-axis geomagnetometer; (2) modeling signals of the accelerometers, the gyroscopes and the geomagnetometers respectively, and filtering and converting the signals; (3) calculating displacement rotation features in a three-dimensional space by using a complementary Kalman filter fusion algorithm, calculating the positions of limbs relative to the space in combination with the spatial displacement and rotation features, and mapping the calculated feature parameters to the corresponding limbs to drive the motion of the body in real time. The invention aims to develop an accurate and efficient multi-sensordata fusion algorithm to solve the problems of low precision, response lag and the like in the conventional inertial motion capture, and to provide some reference for the development of related fields.

Description

technical field [0001] The present invention relates to multiple fields, specifically, it is an application field in which multiple disciplines and technologies intersect and combine, involving electronics, communication, control, computer graphics, ergonomics, navigation and other disciplines. It is a kind of efficient human-computer interaction method constructed with micro-electromechanical inertial components. It is a new research hotspot in the field of human-computer interaction. Background technique [0002] Motion capture technology refers to the collection and processing of the experimenter's body movement data and even rich facial expression data, and using these body movement or facial expression data to drive a virtual three-dimensional human body model to realize the simulation of human movement. Motion capture technology mainly refers to the use of computer-aided, comprehensive motion computer graphics, electronics, ergonomics, optics, mechanics and other tech...

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, the inventors found that the existing motion capture technology at least has defects such as attitude data drift, poor remote controllability, and weak real-time performance.

Images