A Task-Oriented Deep Learning Approach for Human Localization

Abstract

Radio-based human sensing has attracted substantial research attention due to its wide range of applications, including e-healthcare monitoring, indoor security, and industrial surveillance. However, most existing studies rely on fixed receivers to capture wireless signal perturbations. This article introduces UH-Sense, the first human sensing system using an unmanned aerial vehicle (UAV) equipped with an omnidirectional antenna to measure signal strength from surrounding WiFi access points (APs). UH-Sense addresses the challenge of multisource UAV-induced noise with a novel data-driven learning-based approach that denoises corrupted data without prior knowledge of noise characteristics. Furthermore, we develop a localization model based on radio tomography imaging (RTI) that localizes humans without collecting the fingerprint database. We demonstrate that UH-Sense is readily deployable on commodity platforms and evaluate its performance in different real-world environments including irregular AP deployment and nonline-of-sight (NLOS) scenarios. Experimental results show that UH-Sense achieves a high detection performance with an average F1 score of 0.93 and yields similar or even better localization performance than that of using clean data (i.e., data collected at a fixed receiver), which has not been achieved by any of the state-of-the-art denoising methods.