A Maximum-Information-Minimum-Redundancy-Based Feature Fusion Framework for Ship Classification in Moderate-Resolution SAR Image
High-resolution synthetic aperture radar (SAR) images are mostly used in the current field of ship classification, but in practical applications, moderate-resolution SAR images that can offer wider swath are more suitable for maritime surveillance. The ship targets in moderate-resolution SAR images...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/2/519 |
| _version_ | 1827601471116410880 |
|---|---|
| author | Gaoyu Zhou Gong Zhang Biao Xue |
| author_facet | Gaoyu Zhou Gong Zhang Biao Xue |
| author_sort | Gaoyu Zhou |
| collection | DOAJ |
| description | High-resolution synthetic aperture radar (SAR) images are mostly used in the current field of ship classification, but in practical applications, moderate-resolution SAR images that can offer wider swath are more suitable for maritime surveillance. The ship targets in moderate-resolution SAR images occupy only a few pixels, and some of them show the shape of bright spots, which brings great difficulty for ship classification. To fully explore the deep-level feature representations of moderate-resolution SAR images and avoid the “dimension disaster”, we innovatively proposed a feature fusion framework based on the classification ability of individual features and the efficiency of overall information representation, called maximum-information-minimum-redundancy (MIMR). First, we applied the Filter method and Kernel Principal Component Analysis (KPCA) method to form two feature subsets representing the best classification ability and the highest information representation efficiency in linear space and nonlinear space. Second, the MIMR feature fusion method is adopted to assign different weights to feature vectors with different physical properties and discriminability. Comprehensive experiments on the open dataset OpenSARShip show that compared with traditional and emerging deep learning methods, the proposed method can effectively fuse non-redundant complementary feature subsets to improve the performance of ship classification in moderate-resolution SAR images. |
| first_indexed | 2024-03-09T04:56:56Z |
| format | Article |
| id | doaj.art-29153c04387b4fe8bfcb8436efa30de3 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T04:56:56Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-29153c04387b4fe8bfcb8436efa30de32023-12-03T13:03:51ZengMDPI AGSensors1424-82202021-01-0121251910.3390/s21020519A Maximum-Information-Minimum-Redundancy-Based Feature Fusion Framework for Ship Classification in Moderate-Resolution SAR ImageGaoyu Zhou0Gong Zhang1Biao Xue2Key Laboratory of Radar Imaging and Microwave Photonics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaKey Laboratory of Radar Imaging and Microwave Photonics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaKey Laboratory of Radar Imaging and Microwave Photonics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaHigh-resolution synthetic aperture radar (SAR) images are mostly used in the current field of ship classification, but in practical applications, moderate-resolution SAR images that can offer wider swath are more suitable for maritime surveillance. The ship targets in moderate-resolution SAR images occupy only a few pixels, and some of them show the shape of bright spots, which brings great difficulty for ship classification. To fully explore the deep-level feature representations of moderate-resolution SAR images and avoid the “dimension disaster”, we innovatively proposed a feature fusion framework based on the classification ability of individual features and the efficiency of overall information representation, called maximum-information-minimum-redundancy (MIMR). First, we applied the Filter method and Kernel Principal Component Analysis (KPCA) method to form two feature subsets representing the best classification ability and the highest information representation efficiency in linear space and nonlinear space. Second, the MIMR feature fusion method is adopted to assign different weights to feature vectors with different physical properties and discriminability. Comprehensive experiments on the open dataset OpenSARShip show that compared with traditional and emerging deep learning methods, the proposed method can effectively fuse non-redundant complementary feature subsets to improve the performance of ship classification in moderate-resolution SAR images.https://www.mdpi.com/1424-8220/21/2/519moderate-resolution SAR imagefeature fusionfilter methodkernel principal component analysis (KPCA)maximum-information-minimum-redundancy (MIMR)ship classification |
| spellingShingle | Gaoyu Zhou Gong Zhang Biao Xue A Maximum-Information-Minimum-Redundancy-Based Feature Fusion Framework for Ship Classification in Moderate-Resolution SAR Image Sensors moderate-resolution SAR image feature fusion filter method kernel principal component analysis (KPCA) maximum-information-minimum-redundancy (MIMR) ship classification |
| title | A Maximum-Information-Minimum-Redundancy-Based Feature Fusion Framework for Ship Classification in Moderate-Resolution SAR Image |
| title_full | A Maximum-Information-Minimum-Redundancy-Based Feature Fusion Framework for Ship Classification in Moderate-Resolution SAR Image |
| title_fullStr | A Maximum-Information-Minimum-Redundancy-Based Feature Fusion Framework for Ship Classification in Moderate-Resolution SAR Image |
| title_full_unstemmed | A Maximum-Information-Minimum-Redundancy-Based Feature Fusion Framework for Ship Classification in Moderate-Resolution SAR Image |
| title_short | A Maximum-Information-Minimum-Redundancy-Based Feature Fusion Framework for Ship Classification in Moderate-Resolution SAR Image |
| title_sort | maximum information minimum redundancy based feature fusion framework for ship classification in moderate resolution sar image |
| topic | moderate-resolution SAR image feature fusion filter method kernel principal component analysis (KPCA) maximum-information-minimum-redundancy (MIMR) ship classification |
| url | https://www.mdpi.com/1424-8220/21/2/519 |
| work_keys_str_mv | AT gaoyuzhou amaximuminformationminimumredundancybasedfeaturefusionframeworkforshipclassificationinmoderateresolutionsarimage AT gongzhang amaximuminformationminimumredundancybasedfeaturefusionframeworkforshipclassificationinmoderateresolutionsarimage AT biaoxue amaximuminformationminimumredundancybasedfeaturefusionframeworkforshipclassificationinmoderateresolutionsarimage AT gaoyuzhou maximuminformationminimumredundancybasedfeaturefusionframeworkforshipclassificationinmoderateresolutionsarimage AT gongzhang maximuminformationminimumredundancybasedfeaturefusionframeworkforshipclassificationinmoderateresolutionsarimage AT biaoxue maximuminformationminimumredundancybasedfeaturefusionframeworkforshipclassificationinmoderateresolutionsarimage |