Posture capture method and apparatus, electronic equipment and storage medium

Abstract

The invention discloses a posture capture method and apparatus, electronic equipment and a storage medium. The posture capture method comprises the following steps: determining a spatial position of each first marking object attached to a shot object, and label information of the first marking object at the part of the shot object; and adjusting an initial posture model by utilizing the spatial position and label information of each first marking object to generate a reference posture model corresponding to the shot object. By adopting the method, the reference posture model of the shot objectcan be generated by utilizing the spatial position and label information of each first marking object, so that the subsequent motion capture is facilitated.

Description

Technical field [0001] The present application relates to the technical field of computer, and more particularly to a posture capture method, device, electronic device, and storage medium. Background technique [0002] With the high-speed development of computer technology, sensor technology, and virtual reality industry, the development of sports capture technology is extremely rapid and the application range is increasing, especially in various fields such as sports industry, game production, animation production, and film special effects. The role forms a new type of art and technology mutual penetration and fusion, and will become a development trend in the future. [0003] In the current optical capture mode, in the actor's body, the mark is placed, and some high-speed infrared cameras acquires the three-dimensional coordinates of the marker point, and the performance of the player is inferred by the three-dimensional coordinates of the marker. In this scheme, it is assumed ...

AI Technical Summary

Problems solved by technology

And it is time-consuming and cumbersome to reconstruct the actor's skeleton model by moving each joint

Existing methods cannot reconstruct a 3D human body model that matches the actor. Since each bone of the human body has muscles attached to it, it is not a rigid body in the strict sense. This deviates from the assumptions of existing optical capture technologies. Therefore, the existing Optical capture technology has some loss of accuracy for the capture of actors' performances

In addition, since the existing optical capture technology cannot reconstruct a 3D human body model that matches the actor, it is impossible to improve the capture accuracy and enhance the robustness by increasing the number of marked points attached to the actor

Images