Learned Off-Grid Imager for Low-Altitude Economy with Cooperative ISAC Network

TL;DR

This paper introduces a novel physics-embedded learning approach for low-altitude UAV surveillance using cooperative cellular networks, significantly improving detection accuracy over traditional compressed sensing methods.

Contribution

It proposes a physics-embedded learning method to reduce off-grid errors and an online hard example mining scheme for better UAV detection in low-altitude airspace.

Findings

Achieves 97.55% UAV detection rate

Outperforms traditional CS-based methods

Effectively mitigates off-grid errors

Abstract

The low-altitude economy is emerging as a key driver of future economic growth, necessitating effective flight activity surveillance using existing mobile cellular network sensing capabilities. However, traditional monostatic and localizationbased sensing methods face challenges in fusing sensing results and matching channel parameters. To address these challenges, we model low-altitude surveillance as a compressed sensing (CS)-based imaging problem by leveraging the cooperation of multiple base stations and the inherent sparsity of aerial images. Additionally, we derive the point spread function to analyze the influences of different antenna, subcarrier, and resolution settings on the imaging performance. Given the random spatial distribution of unmanned aerial vehicles (UAVs), we propose a physics-embedded learning method to mitigate off-grid errors in traditional CS-based approaches. Furthermore, to enhance rare UAV detection in vast low-altitude airspace, we integrate an online hard example mining scheme into the loss function design, enabling the network to adaptively focus on samples with significant discrepancies from the ground truth during training. Simulation results demonstrate the effectiveness of the proposed low-altitude surveillance framework. The proposed physicsembedded learning algorithm achieves a 97.55% detection rate, significantly outperforming traditional CS-based methods under off-grid conditions. Part of the source code for this paper will be soon accessed at https://github.com/kiwi1944/LAEImager.