Vision Transformer for Classification of UAV and Helicopters Using Micro-Doppler Spectrograms in Surveillance Radar

TL;DR

This paper demonstrates that Vision Transformer models can effectively classify UAVs and helicopters from micro-Doppler spectrograms of varying durations, outperforming traditional CNNs, with high accuracy on real surveillance radar data.

Contribution

The study introduces the application of Vision Transformer architecture to classify micro-Doppler spectrograms with different durations, addressing limitations of CNNs in handling variable input sizes.

Findings

ViT achieved 97.76% accuracy in classification.

Denoising improved micro-Doppler feature visibility.

Self-attention maps provided insights into network performance.

Abstract

Machine learning researchers strive to develop better and better algorithms to solve computer vision problems, such as image classification. In recent years, the classification of micro-Doppler spectrograms has also benefited from these findings. Convolutional neural networks (CNNs) became the gold standard for these tasks. Unfortunately, CNNs can work on fixed-resolution images, or they need to resize mismatched images to fit input dimensions. It can become a problem when micro-Doppler spectrograms are generated with e.g. different integration times. The goal of this work was to classify the UAV and helicopters micro-Doppler spectrograms with different duration times, using the Vision Transformer (ViT) architecture. Before that, spectrograms signal-to-noise-ratio and micro-Doppler features visibility were improved by denoising algorithm based on modified Dual Tree Complex Wavelet Transform. The experiments were conducted on real data collected using surveillance, short range, military radar. As a result, it has been shown that the ViT model achieved 97.76\% accuracy for this task. To further interpret the network performance, the raw self-attention maps were analyzed.