Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AirGuard: UAV and Bird Recognition Scheme for Integrated Sensing and Communications System

Hongliang Luo, Zhonghua Chu, Tengyu Zhang, Chuanbin Zhao, Bo Lin, Feifei Gao

Abstract

In this paper, we propose an unmanned aerial vehicle (UAV) and bird recognition scheme with signal processing and deep learning for integrated sensing and communications (ISAC) system. We first provide the basic scene of low-altitude targets monitoring, and formulate the motion equations and echo signals for UAVs and birds. Next, we extract the centralized micro-Doppler (cmD) spectrum and the high resolution range profile (HRRP) of the low-altitude target from the echo signals. Then we design a dual feature fusion enabled low-altitude target recognition network with convolutional neural network (CNN), which employs both the images of cmD spectrum and HRRP as inputs to jointly distinguish between UAV and bird. Meanwhile, we generate 237600 cmD and HRRP image samples to train, validate, and evaluate the designed low-altitude target recognition network. The proposed scheme is termed as AirGuard, whose effectiveness has been demonstrated by simulation results.

AirGuard: UAV and Bird Recognition Scheme for Integrated Sensing and Communications System

Abstract

In this paper, we propose an unmanned aerial vehicle (UAV) and bird recognition scheme with signal processing and deep learning for integrated sensing and communications (ISAC) system. We first provide the basic scene of low-altitude targets monitoring, and formulate the motion equations and echo signals for UAVs and birds. Next, we extract the centralized micro-Doppler (cmD) spectrum and the high resolution range profile (HRRP) of the low-altitude target from the echo signals. Then we design a dual feature fusion enabled low-altitude target recognition network with convolutional neural network (CNN), which employs both the images of cmD spectrum and HRRP as inputs to jointly distinguish between UAV and bird. Meanwhile, we generate 237600 cmD and HRRP image samples to train, validate, and evaluate the designed low-altitude target recognition network. The proposed scheme is termed as AirGuard, whose effectiveness has been demonstrated by simulation results.
Paper Structure (21 sections, 29 equations, 12 figures)

This paper contains 21 sections, 29 equations, 12 figures.

Table of Contents

  1. Introduction
  2. System Model
  3. ISAC Scene and BS Model
  4. Echo Channel Model of the Extended Target
  5. Echo Signals of UAVs and Birds
  6. Motion Equations and Echo Channels of the UAVs
  7. Motion Equations and Echo Channels of the Birds
  8. Echo Signals of UAVs and Birds
  9. Dual Feature Fusion Enabled Low-Altitude Target Recognition Scheme
  10. cmD Spectrum of Low-Altitude Target
  11. HRRP Sequence Spectrum of Low-Altitude Target
  12. Low-Altitude Target Recognition Network
  13. Computational Complexity Analysis
  14. Simulation Results
  15. UAV and Bird Echo Signal Dataset
  16. ...and 6 more sections

Figures (12)

  • Figure 1: ISAC scenario for low-altitude target monitoring.
  • Figure 2: Process diagram to obtain the UAV calibration point cloud.
  • Figure 3: Update process of UAV motion equations.
  • Figure 4: Process diagram to obtain the bird calibration point cloud.
  • Figure 5: Centralized micro-Doppler spectrum of six different targets. (a) DJI MAVIC 3, a four rotor UAV. (b) Ehang eVTOL, an eight rotor UAV. (c) Six Rotor UAV, a six rotor UAV. (d) Crow. (e) Pigeon. (f) Sparrow. $f_0 = 26$ GHz, $\Delta f=480$ kHz, $M = 4096$, $T_s = 10$ us, $N = 12800$, $N_0 = 128$, $G = 100$.
  • ...and 7 more figures