Stepped Frequency Radar Target Recognition Using Locality Preserving Projections

Abstract:

In this paper, the idea of manifold learning is introduced into Stepped Frequency Radar (SFR) target recognition, a new method based on Locality Preserving Projections (LPP) algorithm and k-nearest neighbour classification for Stepped Frequency Radar target recognition is proposed. LPP is a subspace analytical method based on manifold learning, which is used to reduce the dimension of the High Resolution Range Profile (HRRP) and extract features from HRRP. The feature extraction method by LPP not only preserves the global topology structure, but also captures the local information of the different targets. Then three kinds of target are classified by k-nearest neighbour classification after the LPP. Experimental results on the three different targets suggest that the proposed method has the capability of finding the low-dimensional manifold structure embedded in the high-dimensional HRRP space and can provide a higher recognition rate in Stepped Frequency Radar target recognition.

• Periodical: Applied Mechanics and Materials (Volumes 513-517)
• Pages: 4000-4003
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.513-517.4000
• Online since: February 2014
• Authors: Kun Chen*, Yue Hua Li
• Keywords: HRRP, LPP, Manifold Learning, Stepped Frequency Radar, Target Recognition

References

[1] Li Dan, Long Teng. Target's redundance removed algorithms of step frequency radar. Acta Electronica Sinical, 28(6), pp.60-63, (2000).

[2] Wang Fei, Long Teng. A new target's pick-up algorithm for step frequency radar signal. Journal of Projectiles Rockets Missiles and Guidance, 26(2), pp.135-137, (2006).

[3] Shixi Wang, Zhiguo He. The Fast Target Recognition Approach Based on PCA Features for SAR Images. Journal of National University of Defense Technology, 30, pp.136-140, (2008).

[4] Hualin Liu, Wanlin Yang. Radar Target Recognition Based on Direct Discriminant Analysis Using Range Profile. Chinese Joural of Radio Science, 22, pp.1021-1024, (2007).

[5] Hong Cai, Qiang He, Zhuangzhi Han and Chaoxuan Shang. ISAR target recognition based manifold learning. IET Internaional Radar Conference, pp.1-4, (2009).

DOI: 10.1049/cp.2009.0211

[6] Ming Liu, Yan Wu, Quan Zhao and Lu Gan. SAR target configuration recognition using Locality Preserving Projections. IEEE CIE International Conference on Radar, vol. 1, pp.740-743. (2011).

DOI: 10.1109/cie-radar.2011.6159647

[7] T. M. Cover and P. E. Hart, Nearest neighbor pattern classification. IEEE Trans. Inf, Theory, vol. 13, no. 1, pp.21-27, Jan. (1967).

DOI: 10.1109/tit.1967.1053964

[8] S. T. Roweis, L. K. Saul. Nonlinear Dimensionality Reduction by Locally Linear Embedding. Science, 290, pp.2323-2326, (2000).

DOI: 10.1126/science.290.5500.2323

[9] Tenenbaum J B, De Silva V, and Langford J C. A global geometric framework for nonlinear dimensionality reduction. Science, vol. 290, pp.2319-2323, (2000).

DOI: 10.1126/science.290.5500.2319

[10] He Xiaofei, Partha Niyogi. Locality Preserving Projections. Proc. Conf. Advances in Neural Information Processing Systems 16, Vancouver, Canada, pp.153-160, (2003).

[11] M. Picco, G. Palacio, Unsupervised classification of SAR images using Markov random fields and G01 model. IEEE Geosci. Remote Sens Lett., vol. 8, no. 2, pp.350-353, (2011).

DOI: 10.1109/lgrs.2010.2073678

[12] J. X. Zhou, Z. G. Shi, X, Cheng, and Q. Fu. Automatic target recognition of SAR images based on global scattering center model. IEEE Trans. Geosci. Remote Sens., vol. 49, no. 10, pp.3713-3729, (2011).

DOI: 10.1109/tgrs.2011.2162526