Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cooperative ISAC Network for Off-Grid Imaging-based Low-Altitude Surveillance

Yixuan Huang, Jie Yang, Chao-Kai Wen, Shuqiang Xia, Xiao Li, Shi Jin

TL;DR

This paper tackles low-altitude UAV surveillance by reframing sensing as cooperative CS-based imaging across multiple base stations. It introduces a physics-embedded off-grid imager that first leverages CS priors to generate a preliminary image, then refines it with a CNN that explicitly accounts for off-grid target distributions, guided by an online hard example mining loss. The approach enables non-cooperative target detection, direct image formation from CSI, and scalable fusion across BSs, with simulation results showing substantial gains over traditional on-grid CS methods, especially under off-grid conditions. The work advances practical ISAC-enabled low-altitude surveillance by combining physical modeling, deep learning, and targeted loss design to robustly detect sparse UAVs in large 3D spaces.

Abstract

The low-altitude economy has emerged as a critical focus for future economic development, emphasizing the urgent need for flight activity surveillance utilizing the existing sensing capabilities of mobile cellular networks. Traditional monostatic or localization-based sensing methods, however, encounter challenges in fusing sensing results and matching channel parameters. To address these challenges, we propose an innovative approach that directly draws the radio images of the low-altitude space, leveraging its inherent sparsity with compressed sensing (CS)-based algorithms and the cooperation of multiple base stations. Furthermore, recognizing that unmanned aerial vehicles (UAVs) are randomly distributed in space, we introduce a physics-embedded learning method to overcome off-grid issues inherent in CS-based models. Additionally, an online hard example mining method is incorporated into the design of the loss function, enabling the network to adaptively concentrate on the samples bearing significant discrepancy with the ground truth, thereby enhancing its ability to detect the rare UAVs within the expansive low-altitude space. Simulation results demonstrate the effectiveness of the imaging-based low-altitude surveillance approach, with the proposed physics-embedded learning algorithm significantly outperforming traditional CS-based methods under off-grid conditions.

Cooperative ISAC Network for Off-Grid Imaging-based Low-Altitude Surveillance

TL;DR

This paper tackles low-altitude UAV surveillance by reframing sensing as cooperative CS-based imaging across multiple base stations. It introduces a physics-embedded off-grid imager that first leverages CS priors to generate a preliminary image, then refines it with a CNN that explicitly accounts for off-grid target distributions, guided by an online hard example mining loss. The approach enables non-cooperative target detection, direct image formation from CSI, and scalable fusion across BSs, with simulation results showing substantial gains over traditional on-grid CS methods, especially under off-grid conditions. The work advances practical ISAC-enabled low-altitude surveillance by combining physical modeling, deep learning, and targeted loss design to robustly detect sparse UAVs in large 3D spaces.

Abstract

The low-altitude economy has emerged as a critical focus for future economic development, emphasizing the urgent need for flight activity surveillance utilizing the existing sensing capabilities of mobile cellular networks. Traditional monostatic or localization-based sensing methods, however, encounter challenges in fusing sensing results and matching channel parameters. To address these challenges, we propose an innovative approach that directly draws the radio images of the low-altitude space, leveraging its inherent sparsity with compressed sensing (CS)-based algorithms and the cooperation of multiple base stations. Furthermore, recognizing that unmanned aerial vehicles (UAVs) are randomly distributed in space, we introduce a physics-embedded learning method to overcome off-grid issues inherent in CS-based models. Additionally, an online hard example mining method is incorporated into the design of the loss function, enabling the network to adaptively concentrate on the samples bearing significant discrepancy with the ground truth, thereby enhancing its ability to detect the rare UAVs within the expansive low-altitude space. Simulation results demonstrate the effectiveness of the imaging-based low-altitude surveillance approach, with the proposed physics-embedded learning algorithm significantly outperforming traditional CS-based methods under off-grid conditions.
Paper Structure (18 sections, 16 equations, 6 figures, 1 table, 1 algorithm)

This paper contains 18 sections, 16 equations, 6 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. Signal Model
  4. Channel Model
  5. Learned Model-Driven Off-Grid Imager
  6. CS-Based Problem Formulation
  7. CS-Based Imaging Algorithms
  8. Learned Physics-Embedded Off-Grid Imager
  9. Algorithm Design
  10. Loss Function Design
  11. Numerical Results
  12. Simulation Settings and Metrics
  13. Results and Discussions
  14. Sensing Performance Evaluation of the SP Algorithm under On-Grid Conditions
  15. Sensing Performance Comparison under Off-Grid Conditions
  16. ...and 3 more sections

Figures (6)

  • Figure 1: Illustration of the considered cooperative ISAC network.
  • Figure 2: A 2D illustration of low-altitude space discretization in $xOy$ plane.
  • Figure 3: Illustration of the algorithm flow and the DNN structure.
  • Figure 4: Sensing performance of the SP algorithm under on-grid conditions with varying system configurations.
  • Figure 5: Sensing results of various methods under off-grid conditions.
  • ...and 1 more figures

Theorems & Definitions (1)

  • Remark 1