Ground Moving Radar Targets Classification Based on Spectrogram Images Using Convolutional Neural Networks

In this paper, a new approach for classifying ground moving targets captured by Pulsed Doppler Radars is proposed. Radar echo signals express the doppler effect produced by the movement of targets. Those signals can be processed in different domains to attain distinctive characteristics of targets that can be used for target classification. Our proposed approach is based on utilizing a pre-trained Convolutional Neural Network (CNN), VGG16 and VGG19, as feature extractors whereas the output features were used to train a multiclass support vector machine (SVM) classifier. To evaluate our approach, we used RadEch database of 8 ground moving targets classes. Our approach outperformed the state of the art methods, using the same database, with an accuracy of 96.56%.

[1]  Jeehyun Lee,et al.  Classification Algorithms for Human and Dog Movement Based on Micro-Doppler Signals , 2017 .

[2]  K. Egiazarian,et al.  Classification of ground moving radar targets by using joint time-frequency analysis , 2012, 2012 IEEE Radar Conference.

[3]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  M. Skolnik,et al.  Introduction to Radar Systems , 2021, Advances in Adaptive Radar Detection and Range Estimation.

[5]  Carmine Clemente,et al.  A novel algorithm for radar classification based on doppler characteristics exploiting orthogonal Pseudo-Zernike polynomials , 2015, IEEE Transactions on Aerospace and Electronic Systems.

[6]  Amina Serir,et al.  Micro-doppler radar signature classification by time-frequency and time-scale analysis , 2012, 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).

[7]  Andrew Zisserman,et al.  Trusting SVM for Piecewise Linear CNNs , 2016, ICLR.

[8]  Milenko S. Andric,et al.  Cepstrum-based analysis of radar Doppler signals , 2011, 2011 10th International Conference on Telecommunication in Modern Satellite Cable and Broadcasting Services (TELSIKS).

[9]  Carmine Clemente,et al.  Robust PCA micro-doppler classification using SVM on embedded systems , 2014, IEEE Transactions on Aerospace and Electronic Systems.

[10]  Bojan Zrnic,et al.  Acoustic Experimental Data Analysis Of Moving Targets Echoes Observed By Doppler Radars , 2012 .

[11]  S. Bjorklund,et al.  Evaluation of a micro-Doppler classification method on mm-wave data , 2012, 2012 IEEE Radar Conference.

[12]  Bojan Zrnic,et al.  Analysis of Radar Doppler Signature from Human Data , 2014 .

[13]  Carmine Clemente,et al.  Micro-Doppler based target classification using multi-feature integration , 2013 .

[14]  Seong-Ook Park,et al.  Drone Classification Using Convolutional Neural Networks With Merged Doppler Images , 2017, IEEE Geoscience and Remote Sensing Letters.

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Gustaf Hendeby,et al.  Features for micro-Doppler based activity classification , 2015 .

[18]  Fabrizio Cuccoli,et al.  Vehicle classification based on convolutional networks applied to FM-CW radar signals , 2017, TRAP.

[19]  B. Bondzulic,et al.  Feature Extraction Related to Target Classification for a Radar Doppler Echoes , 2010 .

[20]  Milenko S. Andric,et al.  The database of radar echoes from various targets with spectral analysis , 2010, 10th Symposium on Neural Network Applications in Electrical Engineering.

[21]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[22]  Fulvio Gini,et al.  Knowledge-Based Radar Detection, Tracking, and Classification: Gini/Radar Detection , 2008 .