Polarimetric radar target recognition framework based on LSTM
Polarimetric information is of great importance for radar target recognition. Conventional polarimetric features are hand-designed based on scattering mechanism. In this study, a novel polarimetric target recognition framework based on long–short-term memory (LSTM) network is proposed. The different...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-09-01
|
| Series: | The Journal of Engineering |
| Subjects: | |
| Online Access: | https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0747 |
| _version_ | 1819298185692053504 |
|---|---|
| author | Wei Chen Liang Zhang Jia Song Yanhua Wang Yang Li |
| author_facet | Wei Chen Liang Zhang Jia Song Yanhua Wang Yang Li |
| author_sort | Wei Chen |
| collection | DOAJ |
| description | Polarimetric information is of great importance for radar target recognition. Conventional polarimetric features are hand-designed based on scattering mechanism. In this study, a novel polarimetric target recognition framework based on long–short-term memory (LSTM) network is proposed. The different polarimetric channels are regarded as the sequential inputs in LSTM, and the features are extracted automatically. Experimental results on dual-polarised high-resolution range profile recognition demonstrate that the features learnt by LSTM are more discriminating than conventional features. The recognition performance of the proposed method outperforms the state-of-the-art methods as well. |
| first_indexed | 2024-12-24T05:25:53Z |
| format | Article |
| id | doaj.art-070ba59a609c4aa580f5e50b78196d80 |
| institution | Directory Open Access Journal |
| issn | 2051-3305 |
| language | English |
| last_indexed | 2024-12-24T05:25:53Z |
| publishDate | 2019-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Journal of Engineering |
| spelling | doaj.art-070ba59a609c4aa580f5e50b78196d802022-12-21T17:13:20ZengWileyThe Journal of Engineering2051-33052019-09-0110.1049/joe.2019.0747JOE.2019.0747Polarimetric radar target recognition framework based on LSTMWei Chen0Liang Zhang1Jia Song2Yanhua Wang3Yang Li4Beijing Institute of TechnologyBeijing Institute of TechnologyBeijing Institute of TechnologyBeijing Institute of TechnologyBeijing Institute of TechnologyPolarimetric information is of great importance for radar target recognition. Conventional polarimetric features are hand-designed based on scattering mechanism. In this study, a novel polarimetric target recognition framework based on long–short-term memory (LSTM) network is proposed. The different polarimetric channels are regarded as the sequential inputs in LSTM, and the features are extracted automatically. Experimental results on dual-polarised high-resolution range profile recognition demonstrate that the features learnt by LSTM are more discriminating than conventional features. The recognition performance of the proposed method outperforms the state-of-the-art methods as well.https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0747radar imagingradar target recognitionfeature extractionsynthetic aperture radarradar polarimetryscattering mechanismnovel polarimetric target recognition frameworklong–short-term memory networklstmdifferent polarimetric channelsdual-polarised high-resolution range profile recognitionfeatures learntconventional featuresrecognition performancepolarimetric radar target recognition frameworkpolarimetric informationconventional polarimetric featureshand-designed |
| spellingShingle | Wei Chen Liang Zhang Jia Song Yanhua Wang Yang Li Polarimetric radar target recognition framework based on LSTM The Journal of Engineering radar imaging radar target recognition feature extraction synthetic aperture radar radar polarimetry scattering mechanism novel polarimetric target recognition framework long–short-term memory network lstm different polarimetric channels dual-polarised high-resolution range profile recognition features learnt conventional features recognition performance polarimetric radar target recognition framework polarimetric information conventional polarimetric features hand-designed |
| title | Polarimetric radar target recognition framework based on LSTM |
| title_full | Polarimetric radar target recognition framework based on LSTM |
| title_fullStr | Polarimetric radar target recognition framework based on LSTM |
| title_full_unstemmed | Polarimetric radar target recognition framework based on LSTM |
| title_short | Polarimetric radar target recognition framework based on LSTM |
| title_sort | polarimetric radar target recognition framework based on lstm |
| topic | radar imaging radar target recognition feature extraction synthetic aperture radar radar polarimetry scattering mechanism novel polarimetric target recognition framework long–short-term memory network lstm different polarimetric channels dual-polarised high-resolution range profile recognition features learnt conventional features recognition performance polarimetric radar target recognition framework polarimetric information conventional polarimetric features hand-designed |
| url | https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0747 |
| work_keys_str_mv | AT weichen polarimetricradartargetrecognitionframeworkbasedonlstm AT liangzhang polarimetricradartargetrecognitionframeworkbasedonlstm AT jiasong polarimetricradartargetrecognitionframeworkbasedonlstm AT yanhuawang polarimetricradartargetrecognitionframeworkbasedonlstm AT yangli polarimetricradartargetrecognitionframeworkbasedonlstm |