Abstract Radar target recognition technology is a hot topic in modern radar research field. It can provide target information for the instructor or the operator to make the right decision. Due to its structural feature information, high-resolution range profile (HRRP) is widely used in the field of radar automatic target recognition (RATR). In this paper, we introduced a classification method based on kernel principal component analysis and collaborative representation (KPCA_CRC). First, KPCA is used to extract the nonlinear structure of target data and to reduce the data dimensions of the sample. Then, collaborative representation of samples is carried out to further improve the accuracy of target recognition. Experiments have been done on airplane data of a domestic institution. Compared with Fisher discriminant dictionary learning (FDDL) and the algorithm of CRC_RLS, the experimental results of the method of KPCA_CRC show better performance.
Radar Target Recognition Method Based on Kernel Principal Component Analysis and Collaborative Representation
1st ed. 2016
2016-01-01
11 pages
Article/Chapter (Book)
Electronic Resource
English
British Library Conference Proceedings | 2016
|View Independent Face Recognition Based on Kernel Principal Component Analysis of Local Parts
British Library Conference Proceedings | 2005
|Data Reconstruction Based on Robust Kernel Principal Component Analysis
British Library Online Contents | 2010
|Model validation method with multivariate output based on kernel principal component analysis
British Library Online Contents | 2017
|