A new method for automatic target recognition

Author

Jing, Guo ; Xin, Guo ; Pengfei, Luo

Author_Institution

Dept. of Electron. Eng., Nat. Univ. of Defense Technol., Hunan, China

Volume

2

fYear

1997

fDate

14-18 Jul 1997

Firstpage

1019

Abstract

In this paper, a new method is proposed by combining Mellin transform with bispectrum estimation algorithm to obtain robust radar airplane features with respect to noise contamination, changes in target position, minor changes in the target physical structure and so on. Furthermore, the nearest-neighbor (NN) rule is used for classification of radar targets. The results of computer simulation show that this approach has better noise-proofability and higher recognition rate

Keywords

Monte Carlo methods; digital simulation; feature extraction; image recognition; parameter estimation; radar target recognition; simulation; spectral analysis; transforms; Mellin transform; automatic target recognition; bispectrum estimation algorithm; classification; computer simulation; nearest-neighbor rule; noise contamination; noise-proofability; radar targets; recognition rate; robust radar airplane features; target physical structure; target position; Airplanes; Computer vision; Light scattering; Optical scattering; Phase estimation; Radar measurements; Radar scattering; Signal detection; Spectral analysis; Target recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Aerospace and Electronics Conference, 1997. NAECON 1997., Proceedings of the IEEE 1997 National

Conference_Location

Dayton, OH

Print_ISBN

0-7803-3725-5

Type

conf

DOI

10.1109/NAECON.1997.622770

Filename

622770