By Topic

Effect of AR model-based data extrapolation on target recognition performance

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Dong-Hyun Kim ; Dept. of Electr. Eng. & Comput. Sci., Yeungnam Univ., Kyungbuk, South Korea ; Ji-Hoon Bae ; Hyo-Tae Kim

A data extrapolation method is applied to improve the performance of a target recognition scheme based on the central moments of one-dimensional range profiles. We adopt the autoregressive (AR) model to extrapolate the radar cross section data of a target in order to expand the measured data window. It is shown that the resulting high resolution range profiles can enhance target recognition capability, providing a more accurate recognition performance than the multiple signal classification range profile for moderate signal-to-noise ratio SNR ranges. Furthermore, the effects of the AR model-based data extrapolation on target recognition accuracy are carefully analyzed and investigated.

Published in:

Antennas and Propagation, IEEE Transactions on  (Volume:51 ,  Issue: 4 )