Enhanced End-to-End and Consistent Time-Frequency Analysis for Tracking

Abstract

Dual-frequency continuous wave radar, as a promising Internet of Things, has been used for indoor human tracking, activity detection, and smart homes. Previous indoor tracking primarily used short-time Fourier transform (STFT) for instantaneous frequencies extraction. However, STFT has low resolution and suffers from Heisenberg’s uncertainty principle, which limits the positioning accuracy. Therefore, this article introduces an improved time-frequency analysis (TFA) algorithm called UTFA-Net, capable of significantly enhancing time-frequency resolution, potentially outperforming traditional principles, and thus boosting the precision of through-wall radar target tracking. The proposed framework is founded on an end-to-end self-supervised neural network architecture, integrating novel Rényi and consistency loss mechanisms. Meanwhile, we propose a multidimensional spectrogram generation module, short time fusion attention, and a nonlocal module to boost the model’s spectrogram generation capabilities. In order to validate proposed UTFA-Net, a comprehensive set of experiments is undertaken, including simulation tests, ablation studies, and indoor tracking experiments. The results indicate that UTFA-Net surpasses current advanced algorithms in four performance metrics, showcasing the highest tracking accuracy.