计算机技术与发展2024，Vol.34Issue(4)：42-47,6.DOI:10.20165/j.cnki.ISSN1673-629X.2024.0007
基于实时视频流的3D人体姿势和形状估计
3D Human Pose and Shape Estimation Based on Live Video Streams
摘要
Abstract
A 3D human body pose and shape estimation method based on a temporal attention mechanism is proposed to meet the requirements of real-time accuracy and realism in 3D human body pose and shape estimation for applications such as the metaverse,gaming,and virtual reality.First,image features are extracted and input into a motion continuity attention module to better calibrate the time sequence range that requires attention.Then,a real-time feature attention integration module is used to effectively combine the feature representations of the current frame and past frames.Finally,the human parameter regression network is used to obtain the final results,and a graph convolutional generative adversarial network is used to determine whether the model comes from real human motion data.Compared with previous methods based on real-time video streams,the proposed method reduces the acceleration error by an average of 30％on mainstream datasets,while reducing the network parameters and computational complexity by 65％.The proposed method achieves a 3D human body pose and shape estimation speed of 55～60 frames per second in practical tests,providing better user experience and higher application value for applications such as the metaverse,gaming,and virtual reality.关键词
三维人体重建/SMPL模型/实时特征注意力集成/图卷积神经网络/机器学习Key words
3 D human reconstruction/skinned multi-person linear model/real-time feature attention integration/graph convolutional neural network/machine learning分类
信息技术与安全科学引用本文复制引用
朱越,黄海于,罗学义..基于实时视频流的3D人体姿势和形状估计[J].计算机技术与发展,2024,34(4):42-47,6.基金项目
应急管理部消防救援局科技创新项目(2020XFCX29) （2020XFCX29）
