Method and device for adjusting three-dimensional attitude, electronic equipment and storage medium

Abstract

The invention provides a method and a device for adjusting a three-dimensional posture, electronic equipment and a storage medium, relates to the field of artificial intelligence, in particular to a computer vision and deep learning technology, and can be particularly applied to three-dimensional vision and human body driving scenes. The specific implementation scheme is as follows: acquiring a currently recorded video; estimating a plurality of two-dimensional key points and an initial three-dimensional attitude of the virtual three-dimensional model based on the plurality of image frames; performing contact detection on the target part of the virtual three-dimensional model by using the plurality of two-dimensional key points to obtain a detection result; determining a plurality of target three-dimensional key points through the detection result and a plurality of initial three-dimensional key points corresponding to the initial three-dimensional attitude; and adjusting the initial three-dimensional attitude into the target three-dimensional attitude by adopting the plurality of initial three-dimensional key points and the plurality of target three-dimensional key points.

Description

technical field [0001] The present disclosure relates to the field of artificial intelligence, in particular to computer vision and deep learning technology, which can be used in 3D vision and human-driven scenarios, and in particular to a method, device, electronic device, and storage medium for adjusting 3D posture. Background technique [0002] In the field of artificial intelligence, it is often necessary to obtain the three-dimensional pose of the human body. Since the traditional method of estimating the three-dimensional pose of the human body requires the use of complex motion capture equipment, such as motion capture suits, light capture equipment, etc., the device requires relatively simple motion capture technology based on monocular video to be widely used. In this regard, those skilled in the art continue to try various algorithms for estimating the three-dimensional pose of the human body based on monocular video. [0003] In the existing scheme, the algorithm...

AI Technical Summary

Problems solved by technology

[0005] This disclosure provides a method, device, electronic device and storage medium for adjusting three-dimensional posture, to at least solve the problem in the prior art that the algorithm does not target the grounding effect of human feet The optimization of the constraint model leads to the inaccurate estimation of the three-dimensional pose of the human body, and the technical problems of the obvious floating feeling in the movement of the human feet

Images