Data-driven RF Tomography via Cross-modal Sensing and Continual Learning

TL;DR

This paper introduces a novel data-driven RF tomography framework that combines cross-modal sensing and continual learning to improve underground target detection accuracy in dynamic environments.

Contribution

The work presents a new DRIFT framework integrating RF and visual sensors with continual learning for adaptive underground imaging.

Findings

Achieves 2.29 cm average diameter error, 23.2% better than previous methods.

Demonstrates robustness to environmental changes through continual model updates.

Provides publicly available code and dataset for further research.

Abstract

Data-driven radio frequency (RF) tomography has demonstrated significant potential for underground target detection, due to the penetrative nature of RF signals through soil. However, it is still challenging to achieve accurate and robust performance in dynamic environments. In this work, we propose a data-driven radio frequency tomography (DRIFT) framework with the following key components to reconstruct cross section images of underground root tubers, even with significant changes in RF signals. First, we design a cross-modal sensing system with RF and visual sensors, and propose to train an RF tomography deep neural network (DNN) model following the cross-modal learning approach. Then we propose to apply continual learning to automatically update the DNN model, once environment changes are detected in a dynamic environment. Experimental results show that our approach achieves an average equivalent diameter error of 2.29 cm, 23.2% improvement upon the state-of-the-art approach. Our DRIFT code and dataset are publicly available on https://github.com/Data-driven-RTI/DRIFT.