arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.02196cs.CV
收藏

动态惯性姿态估计器(DynaIP):基于稀疏惯性传感器的部件级运动动力学学习以增强人体姿态估计

Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors

Shanghai Jiao Tong University(上海交通大学);University of Southern California(南加州大学)

Yu Zhang, Songpengcheng Xia, Lei Chu, Jiarui Yang, Qi Wu, Ling Pei

AI总结:

针对现有稀疏惯性传感器人体姿态估计依赖合成数据的不足,提出含伪速度回归模型和部件级模型的DynaIP方法,利用多格式真实动捕数据提升泛化性,在五个公开数据集上实现性能突破。

摘要:

本文提出了一种利用稀疏惯性传感器进行人体姿态估计的新方法,解决了以往依赖合成数据的方法存在的缺陷。该方法利用来自不同骨骼格式的多样化真实惯性运动捕捉数据,提升运动多样性与模型泛化能力。该方法包含两个创新组件:用于惯性传感器动态运动捕捉的伪速度回归模型,以及将身体与传感器数据划分为三个区域、各自聚焦其独特特征的部件级模型。该方法在五个公开数据集上表现优于现有最优模型,在DIP-IMU数据集上姿态误差显著降低19%,为基于惯性传感器的人体姿态估计带来显著提升。代码可在https://github.com/dx118/dynaip获取。

英文摘要:

This paper introduces a novel human pose estimation approach using sparse inertial sensors, addressing the shortcomings of previous methods reliant on synthetic data. It leverages a diverse array of real inertial motion capture data from different skeleton formats to improve motion diversity and model generalization. This method features two innovative components: a pseudo-velocity regression model for dynamic motion capture with inertial sensors, and a part-based model dividing the body and sensor data into three regions, each focusing on their unique characteristics. The approach demonstrates superior performance over state-of-the-art models across five public datasets, notably reducing pose error by 19\% on the DIP-IMU dataset, thus representing a significant improvement in inertial sensor-based human pose estimation. Our codes are available at {\url{https://github.com/dx118/dynaip}}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑