Two-Level Feature-Fusion Ship Recognition Strategy Combining HOG Features with Dual-Polarized Data in SAR Images
Due to the inherent characteristics of synthetic aperture radar (SAR) imaging, SAR ship features are not obvious and the category distribution is unbalanced, which makes the task of ship recognition in SAR images quite challenging. To address the above problems, a two-level feature-fusion ship recog...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/18/4393 |
| _version_ | 1797577281362722816 |
|---|---|
| author | Hongtu Xie Jinfeng He Zheng Lu Jun Hu |
| author_facet | Hongtu Xie Jinfeng He Zheng Lu Jun Hu |
| author_sort | Hongtu Xie |
| collection | DOAJ |
| description | Due to the inherent characteristics of synthetic aperture radar (SAR) imaging, SAR ship features are not obvious and the category distribution is unbalanced, which makes the task of ship recognition in SAR images quite challenging. To address the above problems, a two-level feature-fusion ship recognition strategy combining the histogram of oriented gradients (HOG) features with the dual-polarized data in the SAR images is proposed. The proposed strategy comprehensively utilizes the features extracted by the HOG operator and the shallow and deep features extracted by the Siamese network in the dual-polarized SAR ship images, which can increase the amount of information for the model learning. First, the Siamese network is used to extract the shallow and deep features from the dual-polarized SAR images, and then the HOG feature of the dual-polarized SAR images is also extracted. Furthermore, the bilinear transformation layer is used for fusing the HOG features from dual-polarized SAR images, and the grouping bilinear pooling process is used for fusing the dual-polarized shallow feature and deep feature extracted by the Siamese network, respectively. Finally, the catenation operation is used for fusing the dual-polarized HOG features and dual-polarized shallow feature and deep feature, respectively, which are used for the recognition of the SAR ship targets. Experimental results tested on the OpenSARShip2.0 dataset demonstrate the correctness and effectiveness of the proposed strategy, which can effectively improve the recognition performance of the ship targets by fusing the different level features of the dual-polarized SAR images. |
| first_indexed | 2024-03-10T22:06:00Z |
| format | Article |
| id | doaj.art-08849d353b74445da318a1a83623eb72 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T22:06:00Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-08849d353b74445da318a1a83623eb722023-11-19T12:47:04ZengMDPI AGRemote Sensing2072-42922023-09-011518439310.3390/rs15184393Two-Level Feature-Fusion Ship Recognition Strategy Combining HOG Features with Dual-Polarized Data in SAR ImagesHongtu Xie0Jinfeng He1Zheng Lu2Jun Hu3School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen 518107, ChinaSchool of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen 518107, ChinaInstitute of Remote Sensing Satellite, China Academy of Space Technology, Beijing 100094, ChinaSchool of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen 518107, ChinaDue to the inherent characteristics of synthetic aperture radar (SAR) imaging, SAR ship features are not obvious and the category distribution is unbalanced, which makes the task of ship recognition in SAR images quite challenging. To address the above problems, a two-level feature-fusion ship recognition strategy combining the histogram of oriented gradients (HOG) features with the dual-polarized data in the SAR images is proposed. The proposed strategy comprehensively utilizes the features extracted by the HOG operator and the shallow and deep features extracted by the Siamese network in the dual-polarized SAR ship images, which can increase the amount of information for the model learning. First, the Siamese network is used to extract the shallow and deep features from the dual-polarized SAR images, and then the HOG feature of the dual-polarized SAR images is also extracted. Furthermore, the bilinear transformation layer is used for fusing the HOG features from dual-polarized SAR images, and the grouping bilinear pooling process is used for fusing the dual-polarized shallow feature and deep feature extracted by the Siamese network, respectively. Finally, the catenation operation is used for fusing the dual-polarized HOG features and dual-polarized shallow feature and deep feature, respectively, which are used for the recognition of the SAR ship targets. Experimental results tested on the OpenSARShip2.0 dataset demonstrate the correctness and effectiveness of the proposed strategy, which can effectively improve the recognition performance of the ship targets by fusing the different level features of the dual-polarized SAR images.https://www.mdpi.com/2072-4292/15/18/4393synthetic aperture radar (SAR)two-level feature-fusionSAR ship recognitionhistogram of oriented gradients (HOG) featuresdual-polarized SAR ship images |
| spellingShingle | Hongtu Xie Jinfeng He Zheng Lu Jun Hu Two-Level Feature-Fusion Ship Recognition Strategy Combining HOG Features with Dual-Polarized Data in SAR Images Remote Sensing synthetic aperture radar (SAR) two-level feature-fusion SAR ship recognition histogram of oriented gradients (HOG) features dual-polarized SAR ship images |
| title | Two-Level Feature-Fusion Ship Recognition Strategy Combining HOG Features with Dual-Polarized Data in SAR Images |
| title_full | Two-Level Feature-Fusion Ship Recognition Strategy Combining HOG Features with Dual-Polarized Data in SAR Images |
| title_fullStr | Two-Level Feature-Fusion Ship Recognition Strategy Combining HOG Features with Dual-Polarized Data in SAR Images |
| title_full_unstemmed | Two-Level Feature-Fusion Ship Recognition Strategy Combining HOG Features with Dual-Polarized Data in SAR Images |
| title_short | Two-Level Feature-Fusion Ship Recognition Strategy Combining HOG Features with Dual-Polarized Data in SAR Images |
| title_sort | two level feature fusion ship recognition strategy combining hog features with dual polarized data in sar images |
| topic | synthetic aperture radar (SAR) two-level feature-fusion SAR ship recognition histogram of oriented gradients (HOG) features dual-polarized SAR ship images |
| url | https://www.mdpi.com/2072-4292/15/18/4393 |
| work_keys_str_mv | AT hongtuxie twolevelfeaturefusionshiprecognitionstrategycombininghogfeatureswithdualpolarizeddatainsarimages AT jinfenghe twolevelfeaturefusionshiprecognitionstrategycombininghogfeatureswithdualpolarizeddatainsarimages AT zhenglu twolevelfeaturefusionshiprecognitionstrategycombininghogfeatureswithdualpolarizeddatainsarimages AT junhu twolevelfeaturefusionshiprecognitionstrategycombininghogfeatureswithdualpolarizeddatainsarimages |