DocumentCode
2885942
Title
A superresolution range-Doppler imaging method via neural network completely
Author
Jinsong, Tang ; ZhaoDa, Zhu
Author_Institution
Dept. of Electron. Eng., Nanjing Univ. of Aeronaut. & Astronaut., China
fYear
1996
fDate
8-10 Oct 1996
Firstpage
690
Lastpage
693
Abstract
This paper presents a method of superresolution range-Doppler imaging via a neural network. It is characterized by the following. (1) The forward and backward linear prediction (FBLP) equation is introduced to superresolution imaging. (2) The Tank-Hopfield (1986) network is used to solve the FBLP equation. (3) The process of data extrapolating and DFT are finished by a simple network, which is one part of the T-H network. The digital simulation shows that the method is valid
Keywords
Doppler effect; Hopfield neural nets; discrete Fourier transforms; image resolution; prediction theory; radar computing; radar imaging; DFT; FBLP equation; Tank-Hopfield network; backward linear prediction equation; data extrapolation; digital simulation; forward linear prediction equation; neural network; superresolution range-Doppler imaging; Capacitive sensors; Covariance matrix; Digital simulation; Discrete Fourier transforms; Equations; Image recognition; Image resolution; Neural networks; Transconductance; Vectors;
fLanguage
English
Publisher
ieee
Conference_Titel
Radar, 1996. Proceedings., CIE International Conference of
Conference_Location
Beijing
Print_ISBN
0-7803-2914-7
Type
conf
DOI
10.1109/ICR.1996.574581
Filename
574581
Link To Document