Skeleton animation data processing method and device and communication equipment

Abstract

The invention provides a skeleton animation data processing method and device and communication equipment. The method comprises the steps: obtaining a unit direction vector of each skeleton of a human body according to movement capture data; inputting the unit direction vector of each skeleton of the human body into a target neural network model, and obtaining a first global rotation amount of each joint of the human body output by the target neural network model; according to the first global rotation amount of each joint of the human body and the three-dimensional coordinates of the root joint of the human body, obtaining the position information of the root joint of the virtual character and the second global rotation amount of each joint of the virtual character; wherein the three-dimensional coordinates of the human body root joint are extracted from movement capture data; driving a virtual character skeleton to move according to the position information of the virtual character root joint and the second global rotation amount of each joint of the virtual character; according to the method, a target neural network model determined based on deep learning is utilized to realize mapping from three-dimensional coordinates of a human skeleton to a global rotation amount.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a processing method, device and communication equipment for skeletal animation data. Background technique [0002] In the current field of animation technology, it is a research direction to drive animation characters to do action imitation based on the posture of real people. One of the important links is to convert the 3D coordinates obtained from the joints of real people into the rotation matrix of the corresponding joints, and then apply it to the animation character to drive the movement of the model's limbs. The traditional geometric algorithm is to directly calculate the rotation matrix between vectors, but it ignores that the joints of animators should have certain human dynamic constraints, which cannot guarantee their naturalness and authenticity. Some researchers also try to use kinematics methods Constraints are imposed on each joint, but it is cumber...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the embodiments of the present invention is to provide a processing method, device and communication equipment for skeletal animation data, so as to solve the problem that the traditional geometric algorithm cannot guarantee the naturalness and authenticity of each joint

Images