Conventional target recognition methods usually suffer from information-loss and target-aspect sensitivity when applied to radar high resolution range profile (HRRP) recognition. Thus, Effective establishment of robust and discriminatory feature representation has a significant performance improvement of practical radar applications. In this work, we present a novel feature extraction method, based on modified collaborative auto-encoder, for millimeter-wave radar HRRP recognition. The latent frame-specific weight vector is trained for samples in a frame, which contributes to retaining local information for different targets. Experimental results demonstrate that the proposed algorithm obtains higher target recognition accuracy than conventional target recognition algorithms.
Yilu MA
Nanjing University of Science and Technology
Zhihui YE
Nanjing University of Science and Technology
Yuehua LI
Nanjing University of Science and Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Yilu MA, Zhihui YE, Yuehua LI, "Millimeter-Wave Radar Target Recognition Algorithm Based on Collaborative Auto-Encoder" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 1, pp. 202-205, January 2019, doi: 10.1587/transinf.2018EDL8142.
Abstract: Conventional target recognition methods usually suffer from information-loss and target-aspect sensitivity when applied to radar high resolution range profile (HRRP) recognition. Thus, Effective establishment of robust and discriminatory feature representation has a significant performance improvement of practical radar applications. In this work, we present a novel feature extraction method, based on modified collaborative auto-encoder, for millimeter-wave radar HRRP recognition. The latent frame-specific weight vector is trained for samples in a frame, which contributes to retaining local information for different targets. Experimental results demonstrate that the proposed algorithm obtains higher target recognition accuracy than conventional target recognition algorithms.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDL8142/_p
Copy
@ARTICLE{e102-d_1_202,
author={Yilu MA, Zhihui YE, Yuehua LI, },
journal={IEICE TRANSACTIONS on Information},
title={Millimeter-Wave Radar Target Recognition Algorithm Based on Collaborative Auto-Encoder},
year={2019},
volume={E102-D},
number={1},
pages={202-205},
abstract={Conventional target recognition methods usually suffer from information-loss and target-aspect sensitivity when applied to radar high resolution range profile (HRRP) recognition. Thus, Effective establishment of robust and discriminatory feature representation has a significant performance improvement of practical radar applications. In this work, we present a novel feature extraction method, based on modified collaborative auto-encoder, for millimeter-wave radar HRRP recognition. The latent frame-specific weight vector is trained for samples in a frame, which contributes to retaining local information for different targets. Experimental results demonstrate that the proposed algorithm obtains higher target recognition accuracy than conventional target recognition algorithms.},
keywords={},
doi={10.1587/transinf.2018EDL8142},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - Millimeter-Wave Radar Target Recognition Algorithm Based on Collaborative Auto-Encoder
T2 - IEICE TRANSACTIONS on Information
SP - 202
EP - 205
AU - Yilu MA
AU - Zhihui YE
AU - Yuehua LI
PY - 2019
DO - 10.1587/transinf.2018EDL8142
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2019
AB - Conventional target recognition methods usually suffer from information-loss and target-aspect sensitivity when applied to radar high resolution range profile (HRRP) recognition. Thus, Effective establishment of robust and discriminatory feature representation has a significant performance improvement of practical radar applications. In this work, we present a novel feature extraction method, based on modified collaborative auto-encoder, for millimeter-wave radar HRRP recognition. The latent frame-specific weight vector is trained for samples in a frame, which contributes to retaining local information for different targets. Experimental results demonstrate that the proposed algorithm obtains higher target recognition accuracy than conventional target recognition algorithms.
ER -