Squeeze-and-Excitation Laplacian Pyramid Network With Dual-Polarization Feature Fusion for Ship Classification in SAR Images
| Autor: | Tianwen Zhang, Xiaoling Zhang |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Synthetic aperture radar
Feature fusion Channel (digital image) business.industry Computer science Pattern recognition Geotechnical Engineering and Engineering Geology Polarization (waves) Dual-polarization interferometry Feature (computer vision) Laplacian pyramid Artificial intelligence Electrical and Electronic Engineering business Excitation |
| Zdroj: | IEEE Geoscience and Remote Sensing Letters. 19:1-5 |
| ISSN: | 1558-0571 1545-598X |
| DOI: | 10.1109/lgrs.2021.3119875 |
| Popis: | This letter proposes a squeeze-and-excitation Laplacian pyramid network with dual-polarization feature fusion (SE-LPN-DPFF) for ship classification in synthetic aperture radar (SAR) images. SE-LPN-DPFF offers three contributions – 1) dual-polarization (VV and VH) feature fusion (DPFF), 2) channel modeling by the squeeze-and-excitation (SE) to balance each polarization feature’s contribution, and 3) Laplacian pyramid network (LPN) to achieve multi-resolution analysis (MRA). Extensive ablation studies can confirm the effectiveness of each contribution. Results on the three- and six-category OpenSARShip datasets reveal the state-of-the-art SAR ship classification performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|