Radar-Spectrogram-Based UAV Classification Using Convolutional Neural Networks

Abstract

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%.

Experimental Assessment of Feature Extraction Techniques Applied to the Identification of Properties of Common Objects, Using a Radar System

“…Nevertheless, the differences for SVM-G:OB and other feature sets with SVM-G are smaller than the critical difference. Figures [10][11][12] show the Bayesian Signed-Rank Tests posteriors, for the RF, SVM-L, and SVM-G classifiers, respectively, for the difficult datasets. In Figure 10, for RF, the feature sets with more favorable results when compared to (OB) are (t), (OT), (Ot), and (All), with a probability of 1.000 for the corresponding feature set, and 0.000 for (OB).…”

“…Even daily or ordinary activities (e.g., cooking, eating, and resting) may be classified using this type of acquisition technology [9]. Usually, human action recognition is made using sensors whose location is fixed, but new approaches using unmanned aerial vehicles (UAVs) are starting to appear [10].…”

Guest Editorial Special Issue on Time-Sensitive Networks for Unmanned Aircraft Systems

“…It is difficult to identify UAVs since they fly around at low altitudes and with small radar cross sections (LCS); hence, a new identification scheme for UAVs should be devised to overcome the limitation of the existing system. D. Park et al [ 7 ] present a method to employ a deep learning based classification algorithm based on micro-Doppler signature of UAVs represented on radar spectrum images. The proposed scheme was designed to detect and identify UAVs in real time.…”

Sea Clutter Suppression and Target Detection Algorithm of Marine Radar Image Sequence Based on Spatio-Temporal Domain Joint Filtering

“…The time-frequency analysis method uses the principle that sea clutter and target have different time-frequency characteristics in time-frequency domain to suppress sea clutter. Short time Fourier transform [ 46 , 47 ], fractional Fourier transform [ 48 , 49 , 50 , 51 , 52 ] and sparse Fourier transform [ 53 , 54 , 55 ] all belong to this method. This method transforms the time series data on a range bin into time-frequency domain by using different time-frequency transform.…”