HRR target recognition using the geometry information of scattering centers

In this paper, a new approach for target recognition is proposed and tested on backscattering returns of high range resolution (HRR) radar. The feature vector is constructed from the geometry information of the scattering centers extracted from the HRR radar returns of targets. It is found that the...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang Xun, Zhuang Zhaowen, Guo Guirong
Format: Conference Proceeding
Language:English
Subjects:
Data mining
Diffraction
Frequency
Information geometry
Neural networks
Radar cross section
Radar scattering
Scattering parameters
Solid modeling
Target recognition
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a new approach for target recognition is proposed and tested on backscattering returns of high range resolution (HRR) radar. The feature vector is constructed from the geometry information of the scattering centers extracted from the HRR radar returns of targets. It is found that the geometry parameters are more robust to the aspect angle variations than the range profile. The dimension of the feature vector based on the geometry parameters is much smaller than that based on the range profile that can be used as a good feature vector. The algorithm is applied to the recognition of three scaled models of aircraft using a radial basis function (RBF) neural network.
DOI:10.1109/NAECON.1997.622754