In this paper, a feature fusion algorithm is proposed for automatic target recognition based on High Resolution Range Profiles (HRRP). The proposed algorithm employs Convolution Neural Network (CNN) to extract fused feature from the time-frequency features of HRRP automatically. The time-frequency features used include linear transform and bilinear transform. The coding of the CNN's largest output node is the target category, and the output is compared with a threshold to decide whether the target is classified to a pre-known class or an unknown class. Simulations by four different aircraft models show that the proposed feature fusion algorithm has higher target recognition performance than single features.
2. Li, H. J. and S. H. Yang, "Using range profiles as feature vectors to identify aerospace objects," IEEE Trans. Antennas Propag., Vol. 41, No. 3, 261-268, 1993.
3. Wang, J., Y. Li, and K. Chen, "Radar high-resolution range profile recognition via geodesic weighted sparse representation," IET Radar, Sonar Navig., Vol. 9, No. 1, 75-83, 2015.
4. Zyweck, A. and R. E. Bogner, "Radar target classification of commercial aircraft," IEEE Trans. Aerosp. Electron. Syst., Vol. 32, No. 2, 598-606, 1996.
5. Kim, K. T., D. K. Seo, and H. T. Kim, "Efficient radar target recognition using the MUSIC algorithm and invariant features," IEEE Trans. Antennas Propag., Vol. 50, No. 3, 325-337, 2002.
6. Guo, Z. and S. Li, "One-dimensional frequency-domain features for aircraft recognition from radar range profiles," IEEE Trans. Aerosp. Electron. Syst., Vol. 46, No. 4, 1880-1892, 2010.
7. Chen, V. C. and D. C. Washington, "Radar range profile analysis with natural frame time-frequency representation," Proc. SPIE Wavelet Appl. IV, Vol. 3078, 433-448, 1997.
8. Du, L., Y. Ma, B. Wang, and H. Liu, "Noise-robust classification of ground moving targets based on time-frequency feature from micro-doppler signature," IEEE Sens. J., Vol. 14, No. 8, 2672-2682, 2014.
9. Han, S. K. and H. T. Kim, "Efficient radar target recognition using a combination of range profile and time-frequency analysis," Progress In Electromagnetics Research, Vol. 108, 131-140, 2010.
10. Zhang, X., Z. Liu, S. Liu, and G. Li, "Time-frequency feature extraction of HRRP using AGR and NMF for SAR ATR," Journal of Electrical and Computer Engineering, Vol. 2015, 1-10, 2015.
11. Kim, K., I. Choi, and H. Kim, "Efficient radar target classification using adaptive joint time-frequency processing," IEEE Trans. Antennas Propag., Vol. 48, No. 12, 1789-1801, 2000.
12. Thayaparan, T., et al., "Analysis of radar micro-Doppler signatures from experimental helicopter and human data," Eur. Signal Process. Conf., 289-299, 2006.
13. Lampropoulos, G. A., T. Thayaparan, and N. Xie, "Fusion of time-frequency distributions and applications to radar signals," J. Electron. Imaging, Vol. 15, No. 2, 1-17, 2006.
14. Sejdic, E., I. Djurovic, and J. Jiang, "Time-frequency feature representation using energy concentration: An overview of recent advances," Digit. Signal Process. A Rev. J., Vol. 19, No. 1, 153-183, 2009.
15. Guo, Z., D. Li, and B. Zhang, "Survey of radar target recognition using one-dimensional high range resolution profiles," Systems Engineering and Electronics, Vol. 35, No. 1, 53-60, 2013.
16. LeCun, Y., L. Bottou, Y. Bengio, and P. Haffner, "Gradient based learning applied to document recognition," Proc. IEEE, Vol. 86, No. 11, 2278-2324, 1998.
17. LeCun, Y., Y. Bengio, and G. Hinton, "Deep learning," Nat. Methods, Vol. 521, 436-447, 2015.
18. Lunden, J. and V. Koivunen, "Deep learning for HRRP-based target recognition in multistatic radar systems," IEEE Radar Conf., 2016.