Drone Target Detection Method Using U-Net for DTV-Based Passive Radar 


Vol. 47,  No. 10, pp. 1620-1628, Oct.  2022
10.7840/kics.2022.47.10.1620


PDF
  Abstract

A passive bistatic radar estimates the position and the speed of a target using commercial broadcasting or communication signals. Since DTV (digital television) signal has a stronger signal power and broader bandwidth than other signals, it can be useful for a passive radar when detecting small objects with low-speed such as drones. A radar system generally exploits a CFAR (constant false alarm rate) detector to find a target in the range-Doppler map. However, because of various false detections caused by noise and clutter signals, the false alarm probability of the CFAR detector increases. This paper proposes a target detector based on U-Net, a neural network model used in semantic segmentation, to solve the problem. The proposed target detector can achieve a lower false alarm probability and have a higher target detection probability than the CFAR detector. We present the outstanding results of the artificial-neural-network-based target detector by comparing the CFAR detector’s performances in terms of detection probability, false alarm probability, and F1 score through simulation and real drone data.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

J. Park, D. Park, J. Bang, H. Kim, "Drone Target Detection Method Using U-Net for DTV-Based Passive Radar," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 10, pp. 1620-1628, 2022. DOI: 10.7840/kics.2022.47.10.1620.

[ACM Style]

Ji-Hun Park, Do-Hyun Park, Jong-Hyeon Bang, and Hyoung-Nam Kim. 2022. Drone Target Detection Method Using U-Net for DTV-Based Passive Radar. The Journal of Korean Institute of Communications and Information Sciences, 47, 10, (2022), 1620-1628. DOI: 10.7840/kics.2022.47.10.1620.

[KICS Style]

Ji-Hun Park, Do-Hyun Park, Jong-Hyeon Bang, Hyoung-Nam Kim, "Drone Target Detection Method Using U-Net for DTV-Based Passive Radar," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 10, pp. 1620-1628, 10. 2022. (https://doi.org/10.7840/kics.2022.47.10.1620)