用深度学习提升惯性传感器人体姿态估计精度，效果媲美顶级商用系统。
Deep Inertial Pose: A deep learning approach for human pose estimation
- 采用混合LSTM-Madgwick架构，直接从传感器数据学习姿态
- 使用高精度传感器时误差低至7.96（四元数角度差）
- 适合可穿戴设备开发与低成本姿态捕捉场景
基于惯性运动捕捉系统因其可穿戴性和无约束使用而日益受到关注。然而，精确的人体关节估计算法需经过多个复杂且依赖专业知识的步骤，导致软件成本高昂，如Xsens Technologies的先进MVN Awinda系统。本文研究利用神经网络抽象姿态估计所需的复杂生物力学模型和解析数学方法。通过对比不同神经网络架构与方法，评估其在低性价比（MPU9250）与高端（Mtw Awinda）磁力、角速率与重力（MARG）传感器上的表现。最有效的方法为分离式混合LSTM-Madgwick，使用Mtw Awinda数据时四元数角度距离误差为7.96。此外进行了消融实验，分析数据增强、输出表示、窗口大小、损失函数及磁力计数据对误差的影响。结果表明，神经网络可被训练以实现与当前最优融合滤波器相当的人体姿态估计性能。
原文摘要 · Abstract (English)
Inertial-based Motion capture system has been attracting growing attention due to its wearability and unsconstrained use. However, accurate human joint estimation demands several complex and expertise demanding steps, which leads to expensive software such as the state-of-the-art MVN Awinda from Xsens Technologies. This work aims to study the use of Neural Networks to abstract the complex biomechanical models and analytical mathematics required for pose estimation. Thus, it presents a comparison of different Neural Network architectures and methodologies to understand how accurately these methods can estimate human pose, using both low cost(MPU9250) and high end (Mtw Awinda) Magnetic, Angular Rate, and Gravity (MARG) sensors. The most efficient method was the Hybrid LSTM-Madgwick detached, which achieved an Quaternion Angle distance error of 7.96, using Mtw Awinda data. Also, an ablation study was conducted to study the impact of data augmentation, output representation, window size, loss function and magnetometer data on the pose estimation error. This work indicates that Neural Networks can be trained to estimate human pose, with results comparable to the state-of-the-art fusion filters.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。