Abstract:The novel subspace method is proposed. Firstly, the input rangeprofiles are transformed into high dimension feature space by nonlinear transformation. Then the canonical subspace is constructed in the high dimension feature space to extract feature for improving performance of classification. Finally, the minimum distance classifier is used to classify aircraft targets. The experimental results on the real data of three kinds of aircrafts show the efficiency of the proposed method.
[1] Li H J, Yang S H. Using Range Profiles as Feature Vectors to Identify Aerospace Objects. IEEE Trans on Antennas and Propagation, 1993, 41(3): 261268 [2] Mitchell R A, Westerkamp J J. Robust Statistical Feature Based Aircraft Identification. IEEE Trans on Aerospace and Electronic Systems, 1999, 35(3): 10771093 [3] Novak L M, Owirka G J. Radar Target Identification Recognition Using an EigenImage Approach // Proc of the IEEE International Radar Conference. Atlanta, USA, 1994: 129131 [4] Liu B Y, Yang W L. Radar Target Recognition Using Canonical Transformation to Extract Features. Proc of the SPIE, 1998, 3545: 368371 [5] Wong S K. NonCooperative Target Recognition in the Frequency Domain. IEE Proc Radar, Sonar and Navigation, 2004, 151(2): 7784 [6] Nelson D E, Starzyk J A, Ensley D D. Iterated Wavelet Transformation and Signal Discrimination for HRR Radar Target Recognition. IEEE Trans on Systems, Man, and Cybernetics, 2003, 33(1): 5257 [7] Suvorova S, Schroeder J. Automated Target Recognition Using the KarhunenLoeve Transform with Invariance. Digital Signal Processing, 2002, 12(2/3): 295306 [8] Huether B M, Gustafson S C, Broussad R P. Wavelet Preprocessing for High Range Resolution Radar Classification. IEEE Trans on Aerospace and Electronic Systems, 2001, 37(4): 13211331 [9] Jacobs S P, Sullivan J A. Automatic Target Recognition Using Sequences of High Range Resolution Radar RangeProfiles. IEEE Trans on Aerospace and Electronic Systems, 2000, 36(2): 364380 [10] Eom K B, Chellappa R. Noncooperative Target Classification Using Hierarchical Modeling of HighRange Resolution Radar Signatures. IEEE Trans on Signal Processing, 1997, 45(9): 23182327 [11] Lu J W, Plataniotis K N, Venetsanopoulos A N. A Kernel Machine Based Approach for MultiView Face Recognition // Proc of the International Conference on Image Processing. New York, USA, 2002, I: 265268