Next Article in Journal
Weed and Corn Seedling Detection in Field Based on Multi Feature Fusion and Support Vector Machine
Next Article in Special Issue
An Optimal Routing Algorithm for Unmanned Aerial Vehicles
Previous Article in Journal
Model-Free Lens Distortion Correction Based on Phase Analysis of Fringe-Patterns
Previous Article in Special Issue
Devising a Distributed Co-Simulator for a Multi-UAV Network
Open AccessArticle

Radar-Spectrogram-Based UAV Classification Using Convolutional Neural Networks

Department of Intelligence and Information, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Korea
*
Author to whom correspondence should be addressed.
Sensors 2021, 21(1), 210; https://doi.org/10.3390/s21010210
Received: 3 November 2020 / Revised: 22 December 2020 / Accepted: 24 December 2020 / Published: 31 December 2020
(This article belongs to the Special Issue Time-Sensitive Networks for Unmanned Aircraft Systems)
With the upsurge in the use of Unmanned Aerial Vehicles (UAVs) in various fields, detecting and identifying them in real-time are becoming important topics. However, the identification of UAVs is difficult due to their characteristics such as low altitude, slow speed, and small radar cross-section (LSS). With the existing deterministic approach, the algorithm becomes complex and requires a large number of computations, making it unsuitable for real-time systems. Hence, effective alternatives enabling real-time identification of these new threats are needed. Deep learning-based classification models learn features from data by themselves and have shown outstanding performance in computer vision tasks. In this paper, we propose a deep learning-based classification model that learns the micro-Doppler signatures (MDS) of targets represented on radar spectrogram images. To enable this, first, we recorded five LSS targets (three types of UAVs and two different types of human activities) with a frequency modulated continuous wave (FMCW) radar in various scenarios. Then, we converted signals into spectrograms in the form of images by Short time Fourier transform (STFT). After the data refinement and augmentation, we made our own radar spectrogram dataset. Secondly, we analyzed characteristics of the radar spectrogram dataset with the ResNet-18 model and designed the ResNet-SP model with less computation, higher accuracy and stability based on the ResNet-18 model. The results show that the proposed ResNet-SP has a training time of 242 s and an accuracy of 83.39%, which is superior to the ResNet-18 that takes 640 s for training with an accuracy of 79.88%. View Full-Text
Keywords: CNN; classification; UAV; FMCW radar; STFT; spectrogram; MDS CNN; classification; UAV; FMCW radar; STFT; spectrogram; MDS
Show Figures

Figure 1

MDPI and ACS Style

Park, D.; Lee, S.; Park, S.; Kwak, N. Radar-Spectrogram-Based UAV Classification Using Convolutional Neural Networks. Sensors 2021, 21, 210. https://doi.org/10.3390/s21010210

AMA Style

Park D, Lee S, Park S, Kwak N. Radar-Spectrogram-Based UAV Classification Using Convolutional Neural Networks. Sensors. 2021; 21(1):210. https://doi.org/10.3390/s21010210

Chicago/Turabian Style

Park, Dongsuk; Lee, Seungeui; Park, SeongUk; Kwak, Nojun. 2021. "Radar-Spectrogram-Based UAV Classification Using Convolutional Neural Networks" Sensors 21, no. 1: 210. https://doi.org/10.3390/s21010210

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop