A Multi-Characteristic Learning Method with Micro-Doppler Signatures for Pedestrian Identification

TL;DR

This paper introduces a multi-characteristic learning model that combines time-Doppler spectrograms and statistical features from FMCW radar to improve pedestrian identification accuracy and stability.

Contribution

The study proposes a novel multi-characteristic learning approach with clustering to effectively fuse micro-Doppler signatures for pedestrian identification.

Findings

Higher accuracy rate than existing methods

More stable pedestrian identification performance

Effective fusion of multiple micro-Doppler features

Abstract

The identification of pedestrians using radar micro-Doppler signatures has become a hot topic in recent years. In this paper, we propose a multi-characteristic learning (MCL) model with clusters to jointly learn discrepant pedestrian micro-Doppler signatures and fuse the knowledge learned from each cluster into final decisions. Time-Doppler spectrogram (TDS) and signal statistical features extracted from FMCW radar, as two categories of micro-Doppler signatures, are used in MCL to learn the micro-motion information inside pedestrians' free walking patterns. The experimental results show that our model achieves a higher accuracy rate and is more stable for pedestrian identification than other studies, which make our model more practical.