Recognition and Classification of Rotorcraft by Micro-Doppler Signatures Using Deep Learning
Detection and classification of rotorcraft targets are of great significance not only in civil fields but also in defense. However, up to now, it is still difficult for the traditional radar signal processing methods to detect and distinguish rotorcraft targets from various types of moving objects. Moreover, it is even more challenging to classify different types of helicopters. As the development of high-precision radar, classification of moving targets by micro-Doppler features has become a promising research topic in the modern signal processing field. In this paper, we propose to use the deep convolutional neural networks (DCNNs) in rotorcraft detection and helicopter classification based on Doppler radar signals. We apply DCNN directly to raw micro-Doppler spectrograms for rotorcraft detection and classification. The proposed DCNNs can learn the features automatically from the micro-Doppler signals without introducing any domain background knowledge. Simulated data are used in the experiments. The experimental results show that the proposed DCNNs achieve superior accuracy in rotorcraft detection and superior accuracy in helicopter classification, outperforming the traditional radar signal processing methods.
KeywordsConvolutional neural network Deep learning Target detection Classification Micro-Doppler
This project was partially supported by Grants from Natural Science Foundation of China #71671178/#91546201/#61202321, and the open project of the Key Lab of Big Data Mining and Knowledge Management. It was also supported by Hainan Provincial Department of Science and Technology under Grant No. ZDKJ2016021, and by Guangdong Provincial Science and Technology Project 2016B010127004.
- 1.Tahmoush, D., Silvious, J.: Radar micro-Doppler for long range front-view gait recognition. In: Proceedings of IEEE 3rd International Conference on Biometrics, Theory, Applications and Systems, 28–30 September, Washington, DC, USA, pp. 1–6 (2009)Google Scholar
- 2.van Dorp, P., Groen, F.C.A.: Human walking estimation with radar. In: Proceedings of Institution of Electrical Engineers—Radar, Sonar Navigation, vol. 150, no. 5, pp. 356–365, October 2003Google Scholar
- 4.Stove, A.G., Sykes, S.R.: Doppler-based automatic target classifier for a battlefield surveillance radar. In: Proceedings of IEEE International Radar Conference, 15–17 October, Edinburgh, U.K., pp. 419–423 (2002)Google Scholar
- 5.Molchanov, P., Astola, J., Egiazarian, K., et al.: Classification of ground moving radar targets by using joint time-frequency analysis. In: Radar Conference (RADAR), pp. 0366–0371 (2012)Google Scholar
- 6.Molchanov, P., Astola, J., Egiazarian, K., et al.: Ground moving target classification by using DCT coefficients extracted from micro-Doppler radar signatures and artificial neuron network. In: Microwaves, Radar and Remote Sensing Symposium (MRRS), pp. 173–176 (2011)Google Scholar
- 8.Thayaparan, T., Abrol, S., Riseborough, E.: Micro-Doppler radar signatures for intelligent target recognition. Defence Research and Development Canadaottawa (Ontario) (2004)Google Scholar
- 11.Mikolov, T., Deoras, A., Povey, D., et al.: Strategies for training large scale neural network language models. In: 2011 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 196–201. IEEE (2011)Google Scholar
- 12.Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
- 13.Sánchez, J., Perronnin, F.: High-dimensional signature compression for large-scale image classification. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1665–1672. IEEE (2011)Google Scholar
- 14.Sun, Y., Chen, Y., Wang, X., et al.: Deep learning face representation by joint identification-verification. In: Advances in Neural Information Processing Systems, pp. 1988–1996 (2014)Google Scholar
- 15.Sun, Y., Wang, X., Tang, X.: Deep learning face representation from predicting 10,000 classes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1891–1898 (2014)Google Scholar
- 17.Chetlur, S., Woolley, C, Vandermersch P, et al.: cuDNN: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)