Motion capture method and system, and storage medium

Abstract

The invention discloses a motion capture method and system, and a storage medium. The motion capture method comprises the following steps of: constructing a first human body model; controlling a motion state of the first human body model according to first posture data uploaded by an inertia sensing module; receiving a first image uploaded by an optical measurement module; extracting a human bodyimage of the first image; calculating to obtain a second human body model according to the human body image; and correcting the motion state of the first human body model according to the second humanbody model. According to the motion capture method, the measurement noise and the migration error of the motion capture system based on the inertial sensor can be reduced under the condition that nomarking point needs to be marked, so that the function of accurately completing motion capture is realized. The motion capture method can be widely applied to the technical field of motion capture.

Description

technical field [0001] The present invention relates to the technical field of motion capture, in particular to a motion capture method, system and storage medium. Background technique [0002] Motion capture is the process of accurately measuring and recording the trajectory or posture of an object in real three-dimensional space in real time, and reconstructing the motion state of the moving object at each moment in virtual three-dimensional space. The most typical application of motion capture is the motion capture of characters in the fields of CG production, games, experiential interactive games, virtual idols, etc. It can perform 3D digital calculation of the body movements of characters to obtain 3D motion data. [0003] In the prior art, there are mainly three motion capture schemes: the first is an optical motion capture system based on markers, which may cause markers to be blocked during the acquisition process, especially when there are many people or there are m...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, there are mainly three kinds of motion capture schemes: the first is an optical motion capture system based on markers, which may cause markers to be blocked during the acquisition process, especially when there are many people or there are more people on the field. In the case of background objects, the possibility of occluding the marked points will greatly increase. After the marked points are occluded, there will be serious posture drift or distortion; the second is a motion capture system based on computer vision, which is easy Affected by ambient light, complex background or multiple targets, the motion capture effect is poor. Due to the limitation of the visual field, the user's movement space is limited to the visual range of the camera, which reduces the practicality; the third One is the motion capture system of inertial sensor, which is easily affected by factors such as measurement noise and wandering error, so it cannot accurately track the posture of the human body for a long time

Images