For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Millimeter-Wave Radar Target Recognition Algorithm Based on Collaborative Auto-Encoder
Yilu MA Zhihui YE Yuehua LI
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2019/01/01
Online ISSN: 1745-1361
Type of Manuscript: LETTER
Category: Pattern Recognition
target recognition, high resolution range profile, auto-encoder, frame-specific weight vector,
Full Text: PDF(481.5KB)
>>Buy this Article
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.