Chirplet-Atoms Network Approach to High-Resolution Range Profiles Automatic Target Recognition

Li, Y.; Guo, Z.; Li, Y; Guo, Z

doi:10.1109/cisp-bmei.2018.8633206

Home

>

Section

>

Chapter

Chirplet-Atoms Network Approach to High-Resolution Range Profiles Automatic Target Recognition

Li, Y.; Guo, Z.

Proceedings - 2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2018: 8633206

2018

ISSN/ISBN: 9781538676042

DOI: 10.1109/cisp-bmei.2018.8633206
Accession: 104113111

Article/Abstract emailed within 0-6 h

Payments are secure & encrypted

Summary

Since radar back-scattering from a real target can be very complex, a Chirplet-atoms network approach to automatic target recognition using high resolution range profiles (HRRP)is proposed in this paper. Based on the multilayer feed-forward neural network structure, the Chirplet-atom transform is used to the input layer for feature extraction, and the hidden layer and output layer constitute a classifier. The network weights and the parameters of Chirplet-atom node are simultaneously adjusted to achieve joint feature extraction and target classification. The simulation results of four aircrafts have shown that the Chirplet-atoms network approach has better recognition rates and noisy immunity.