Convolutional neural networks-based aerial target classification using micro-Doppler profiles

Karabayir, Osman; Kartal, M.; Yucedag, Okan Mert

doi:10.1109/siu.2017.7960173

Cited by 4 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classification of radar targets based on their HRRP has been studied [12][13][14][15][16][17][18][19][20] . A recent study using long short-term memory -recurrent neural network (LSTM-RNN) may be found in Sagayaraj 19 , et al Application of convolutional neural network (CNN) in radar target classification problems based on SAR images and micro doppler signatures have also been studied [23][24][25] . This paper extends the applicability of CNN and LSTM to HRRP.…”

Section: Case Studies 61 Radar Target Classification Based On High-rmentioning

confidence: 99%

A Hybrid Approach to Cognition in Radars

et al. 2018

View full text Add to dashboard Cite

In many engineering domains, cognition is emerging to play vital role. Cognition will play crucial role in radar engineering as well for the development of next generation radars. In this paper, a cognitive architecture for radars is introduced, based on hybrid cognitive architectures. The paper proposes deep learning applications for integrated target classification based on high-resolution radar range profile measurements and target revisit time calculation as case studies. The proposed architecture is based on the artificial cognitive systems concepts and provides a basis for addressing cognition in radars, which is inadequately explored for radar systems. Initial experimental studies on the applicability of deep learning techniques under this approach provided promising results.

show abstract

Section: Case Studies 61 Radar Target Classification Based On High-rmentioning

confidence: 99%

A Hybrid Approach to Cognition in Radars

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Literature [16] realizes the radar ID which can identify specific person using DCNNs. Literature [17] classifies aerials targets based on DCNNs. Apparently, DCNNs can also be utilized to classify UAV-to-Ground vehicles.…”

Section: Introductionmentioning

confidence: 99%

“…Apparently, DCNNs can also be utilized to classify UAV-to-Ground vehicles. In literatures [14]- [17], input of DCNNs is the spectrums obtained by time-frequency methods. Although DCNNs have no strict requirements on image quality, a large amount of noise when signal-to-noise ratio (SNR) is low still affects the feature learning of DCNNs.…”

Section: Introductionmentioning

confidence: 99%

Classification of UAV-to-Ground Vehicles Based on Micro-Doppler Signatures Using Singular Value Decomposition and Deep Convolutional Neural Networks

et al. 2019

View full text Add to dashboard Cite

Attack from the unmanned aerial vehicles (UAVs) has been the main means of high-precision strike. Therefore, classifying ground vehicles from the UAV with high accuracy is of great significance. In order to avoid the complex feature extracting process and realize the classification of UAV-to-ground vehicles in different situations, this paper proposed a method based on micro-Doppler signatures using singular value decomposition (SVD) and deep convolutional neural networks (DCNNs). First, models of UAV-to-ground vehicles are built to analyze the micro-Doppler components and Doppler signals in five different cases are given. Second, time-frequency spectrums of Doppler signals with low signal-to-noise ratios are improved after removing noise using SVD. Third, transfer-learning of pre-trained DCNNs is achieved using measured data and classification under various conditions is realized using the new-trained network. When there is no noise, the overall classification accuracy of two types of Doppler signals, three types of Doppler signals, four types of Doppler signals and five types of Doppler signals has reached 100%, 97%, 97%, and 96%, respectively. Comparison with current methods which need to extract micro-Doppler features by time-frequency techniques are also made. Outstanding performance proves the superiority and robustness of the proposed method. INDEX TERMS Classification, UAV-to-ground vehicles, micro-doppler signatures, singular value decomposition, deep convolutional neural networks.

show abstract