Temporal Micro-Doppler Spectrogram-based ViT Multiclass Target Classification

TL;DR

This paper introduces a novel transformer-based approach for multiclass target classification using micro-Doppler spectrograms from millimeter-wave radar, improving accuracy and efficiency over CNN methods.

Contribution

The paper presents the T-MDS-ViT, a transformer architecture that models spatiotemporal radar data with attention mechanisms, enhancing classification performance and interpretability.

Findings

Outperforms CNN-based methods in accuracy

Achieves better data efficiency

Supports real-time deployment

Abstract

In this paper, we propose a new Temporal MDS-Vision Transformer (T-MDS-ViT) for multiclass target classification using millimeter-wave FMCW radar micro-Doppler spectrograms. Specifically, we design a transformer-based architecture that processes stacked range-velocity-angle (RVA) spatiotemporal tensors via patch embeddings and cross-axis attention mechanisms to explicitly model the sequential nature of MDS data across multiple frames. The T-MDS-ViT exploits mobility-aware constraints in its attention layer correspondences to maintain separability under target overlaps and partial occlusions. Next, we apply an explainable mechanism to examine how the attention layers focus on characteristic high-energy regions of the MDS representations and their effect on class-specific kinematic features. We also demonstrate that our proposed framework is superior to existing CNN-based methods in terms of classification accuracy while achieving better data efficiency and real-time deployability.