TWR-MCAE: A Data Augmentation Method for Through-the-Wall Radar Human Motion Recognition

TL;DR

This paper introduces TWR-MCAE, a novel data augmentation method using a multilink auto-encoding neural network to improve through-the-wall radar human motion recognition accuracy and training efficiency.

Contribution

The paper presents a new neural network-based data augmentation technique combining SVD, attention, and LISTA modules for enhanced feature extraction in TWR systems.

Findings

Improved recognition accuracy in TWR human motion classification.

Faster training convergence of classifiers with the proposed method.

Enhanced PSNR indicating better signal quality.

Abstract

To solve the problems of reduced accuracy and prolonging convergence time of through-the-wall radar (TWR) human motion due to wall attenuation, multipath effect, and system interference, we propose a multilink auto-encoding neural network (TWR-MCAE) data augmentation method. Specifically, the TWR-MCAE algorithm is jointly constructed by a singular value decomposition (SVD)-based data preprocessing module, an improved coordinate attention module, a compressed sensing learnable iterative shrinkage threshold reconstruction algorithm (LISTA) module, and an adaptive weight module. The data preprocessing module achieves wall clutter, human motion features, and noise subspaces separation. The improved coordinate attention module achieves clutter and noise suppression. The LISTA module achieves human motion feature enhancement. The adaptive weight module learns the weights and fuses the three subspaces. The TWR-MCAE can suppress the low-rank characteristics of wall clutter and enhance the sparsity characteristics in human motion at the same time. It can be linked before the classification step to improve the feature extraction capability without adding other prior knowledge or recollecting more data. Experiments show that the proposed algorithm gets a better peak signal-to-noise ratio (PSNR), which increases the recognition accuracy and speeds up the training process of the back-end classifiers.