| 引用本文: | 赵琰,郭明,孙建强,邱建龙.人体动作识别中的惯性传感器位置校正算法[J].控制理论与应用,2021,38(11):1883~1890.[点击复制] |
| ZHAO Yan,GUO Ming,SUN Jian-qiang,QIU Jian-long.Position correction algorithm of inertial sensors in human action recognition[J].Control Theory and Technology,2021,38(11):1883~1890.[点击复制] |
|
| 人体动作识别中的惯性传感器位置校正算法 |
| Position correction algorithm of inertial sensors in human action recognition |
| 摘要点击 1563 全文点击 442 投稿时间：2021-08-25 修订日期：2021-11-23 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/CTA.2021.10793 |
| 2021,38(11):1883-1890 |
| 中文关键词 传感器系统 位置校正 旋转矩阵 动作识别 加权BP神经网络 |
| 英文关键词 sensor system position correction rotation matrix action recognition weighted BP neural network |
| 基金项目 国家自然科学基金项目(61903170, 11805091, 61877033, 61833005), 山东省高等学校青年创新团队发展计划项目资助. |
|
| 中文摘要 |
| 近年来, 惯性传感器在人体动作识别中的应用受到了广泛关注, 但用户在重新穿戴惯性传感器时, 不能保
证每次的固定位置完全一致, 这会影响识别精度. 针对此问题, 本文提出一种利用旋转矩阵实现惯性传感器位置校
正的人体动作识别方法. 首先, 将惯性传感器按照不同的位置固定在手腕处采集动作数据. 然后, 根据矩阵旋转变换
原理, 通过标准固定位置与其他固定位置的基准数据求取旋转矩阵. 最后, 对动作数据提取时频域特征, 并构造加
权BP神经网络模型以验证校正方法的有效性. 同时还讨论了不同的数据融合方法对动作识别的影响. 结果表明, 校
正后的动作数据的识别准确率分别为84.25%, 85.94%, 相比校正前提高了66.16%, 54.35%, 说明该方法是有效的. |
| 英文摘要 |
| In recent years, the application of inertial sensors in human action recognition has received extensive attention,
but users cannot guarantee that the fixed positions are completely consistent each time they wear inertial sensors again,
which can affect the recognition accuracy. Aiming at this problem, this paper proposes a human action recognition method
using rotation matrix to realize the position correction of inertial sensors. Firstly, the inertial sensors are fixed at the wrists
according to different positions to collect action data. Secondly, the rotation matrices are obtained from benchmark data of
the standard fixed position and other fixed positions according to the principle of matrix rotation transformation. Finally, the
time-frequency domain features of the action data are extracted, and the weighted back propagation (BP) neural network
model is constructed to verify the effectiveness of the correction method. It also discusses the influence of different data
fusion methods on action recognition. As a result, the action accuracies of the corrected test data are 84.25%, 85.94%,
which are increased by 66.16%, 54.35% compared with those before correction. It shows that the method is effective. |
|
|
|
|
|