School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Korea.
Department of AI, Chung-Ang University, Seoul 06974, Korea.
Sensors (Basel). 2022 Aug 24;22(17):6363. doi: 10.3390/s22176363.
This paper considers a Deep Convolutional Neural Network (DCNN) with an attention mechanism referred to as Dual-Scale Doppler Attention (DSDA) for human identification given a micro-Doppler (MD) signature induced as input. The MD signature includes unique gait characteristics by different sized body parts moving, as arms and legs move rapidly, while the torso moves slowly. Each person is identified based on his/her unique gait characteristic in the MD signature. DSDA provides attention at different time-frequency resolutions to cater to different MD components composed of both fast-varying and steady. Through this, DSDA can capture the unique gait characteristic of each person used for human identification. We demonstrate the validity of DSDA on a recently published benchmark dataset, IDRad. The empirical results show that the proposed DSDA outperforms previous methods, using a qualitative analysis interpretability on MD signatures.
本文提出了一种基于深度卷积神经网络（DCNN）的注意力机制，称为双尺度多普勒注意力（DSDA），用于对输入的微多普勒（MD）特征进行人体识别。MD 特征包含了由不同大小的身体部位运动引起的独特步态特征，手臂和腿部运动较快，而躯干运动较慢。每个人都可以根据 MD 特征中的独特步态特征来识别。DSDA 在不同的时频分辨率下提供注意力，以适应由快速变化和稳定组成的不同 MD 分量。通过这种方式，DSDA 可以捕获每个人独特的步态特征，用于人体识别。我们在最近发布的基准数据集 IDRad 上验证了 DSDA 的有效性。实验结果表明，与以前的方法相比，所提出的 DSDA 具有更好的性能，通过对 MD 特征进行定性分析可解释性。
