Du Guoming, Ding Zhen, Guo Hao, Song Meichao, Jiang Feng
School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China.
College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China.
Bioengineering (Basel). 2024 Oct 15;11(10):1026. doi: 10.3390/bioengineering11101026.
Estimating human joint angles is a crucial task in motion analysis, gesture recognition, and motion intention prediction. This paper presents a novel model-based approach for generating reliable and accurate human joint angle estimation using a dual-branch network. The proposed network leverages combined features derived from encoded sEMG signals and RGB-D image data. To ensure the accuracy and reliability of the estimation algorithm, the proposed network employs a convolutional autoencoder to generate a high-level compression of sEMG features aimed at motion prediction. Considering the variability in the distribution of sEMG signals, the proposed network introduces a vision-based joint regression network to maintain the stability of combined features. Taking into account latency, occlusion, and shading issues with vision data acquisition, the feature fusion network utilizes high-frequency sEMG features as weights for specific features extracted from image data. The proposed method achieves effective human body joint angle estimation for motion analysis and motion intention prediction by mitigating the effects of non-stationary sEMG signals.
估计人体关节角度是运动分析、手势识别和运动意图预测中的一项关键任务。本文提出了一种基于模型的新颖方法，使用双分支网络生成可靠且准确的人体关节角度估计。所提出的网络利用从编码的表面肌电信号和RGB-D图像数据中导出的组合特征。为确保估计算法的准确性和可靠性，所提出的网络采用卷积自动编码器来生成针对运动预测的表面肌电特征的高级压缩。考虑到表面肌电信号分布的可变性，所提出的网络引入了基于视觉的关节回归网络以维持组合特征的稳定性。考虑到视觉数据采集的延迟、遮挡和阴影问题，特征融合网络利用高频表面肌电特征作为从图像数据中提取的特定特征的权重。所提出的方法通过减轻非平稳表面肌电信号的影响，实现了用于运动分析和运动意图预测的有效的人体关节角度估计。
