Indoor human motion classification by L1-norm subspaces of micro-Doppler signatures
Indoor human motion classification by L1-norm subspaces of micro-Doppler signatures
复制标题
通过微多普勒特征的 L1 范数子空间进行室内人体运动分类
DOI：
10.1109/radar.2017.7944501
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
F. Ahmad
中科院分区：
文献类型：
--
作者：
Panos P. Markopoulos;F. Ahmad
在本文中，我们提出了一种基于雷达的人体运动分类技术，用于患者和老年人的室内监测。所提出的方法采用 L1 范数主成分分析 (L1-PCA) 导出相关微多普勒特征的子空间。 L1-PCA 比标准 PCA 更稳健，能够抵抗处理数据中的异常值。基于真实数据实验的结果表明，当训练数据是标称/干净时，所提出的方法表现出与基于 PCA 的室内人体运动分类相似的性能，而当训练微多普勒特征数据集异常值损坏时，它提供了增强的性能。
In this paper, we propose a radar-based human motion classification technqiue for indoor monitoring of patients and elderly. The proposed method employs L1-norm Principal Component Analysis (L1-PCA) derived subspaces of the associated micro-Doppler signatures. L1-PCA is more robust than standard PCA, exhibiting resistance against outliers among the processed data. Results based on real data experiments demonstrate that the proposed method exhibits performance similar to PCA-based indoor human motion classification when the training data are nominal/clean, while it provides enhanced performance when the training micro-Doppler signature datasets are outlier-corrupted.