Gaussian Function Fusing Fully Convolutional Network and Region Proposal-Based Network for Ship Target Detection in SAR Images
Recently, ship target detection in Synthetic aperture radar (SAR) images has become one of the current research hotspots and plays an important role in the real-time detection of sea regions. The traditional SAR ship detection methods usually consist of two modules, one module named land-sea segment...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | International Journal of Antennas and Propagation |
| Online Access: | http://dx.doi.org/10.1155/2022/3063965 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832553627591376896 |
|---|---|
| author | Peipei Zhang Guokun Xie Jinsong Zhang |
| author_facet | Peipei Zhang Guokun Xie Jinsong Zhang |
| author_sort | Peipei Zhang |
| collection | DOAJ |
| description | Recently, ship target detection in Synthetic aperture radar (SAR) images has become one of the current research hotspots and plays an important role in the real-time detection of sea regions. The traditional SAR ship detection methods usually consist of two modules, one module named land-sea segmentation for removing the complicated land regions, and one module named ship target detection for realizing fine ship detection. An algorithm combining the Unet-based land-sea segmentation method and improved Faster RCNN-based ship detection method is proposed in this paper. The residual convolution module is introduced into the Unet structure to deepen the network level and improve the feature representation ability. The K-means method is introduced in the Faster RCNN method to cluster the size and aspect ratio of ship targets, to improve the anchor frame design, and make it more suitable for our ship detection task. Meanwhile, a fine detection algorithm uses the Gaussian function to fuse the confidence value of sea-land segmentation results and the coarse detection results. The segmentation and detection results on the established segmentation dataset and detection dataset, respectively, demonstrate the effectiveness of our proposed segmentation methods and detection methods. |
| format | Article |
| id | doaj-art-adfd46156d4b43ce98950b94cb70a504 |
| institution | Kabale University |
| issn | 1687-5877 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Antennas and Propagation |
| spelling | doaj-art-adfd46156d4b43ce98950b94cb70a5042025-02-03T05:53:33ZengWileyInternational Journal of Antennas and Propagation1687-58772022-01-01202210.1155/2022/3063965Gaussian Function Fusing Fully Convolutional Network and Region Proposal-Based Network for Ship Target Detection in SAR ImagesPeipei Zhang0Guokun Xie1Jinsong Zhang2ZTE Communication InstituteZTE Communication InstituteNational Laboratory of Radar Signal ProcessingRecently, ship target detection in Synthetic aperture radar (SAR) images has become one of the current research hotspots and plays an important role in the real-time detection of sea regions. The traditional SAR ship detection methods usually consist of two modules, one module named land-sea segmentation for removing the complicated land regions, and one module named ship target detection for realizing fine ship detection. An algorithm combining the Unet-based land-sea segmentation method and improved Faster RCNN-based ship detection method is proposed in this paper. The residual convolution module is introduced into the Unet structure to deepen the network level and improve the feature representation ability. The K-means method is introduced in the Faster RCNN method to cluster the size and aspect ratio of ship targets, to improve the anchor frame design, and make it more suitable for our ship detection task. Meanwhile, a fine detection algorithm uses the Gaussian function to fuse the confidence value of sea-land segmentation results and the coarse detection results. The segmentation and detection results on the established segmentation dataset and detection dataset, respectively, demonstrate the effectiveness of our proposed segmentation methods and detection methods.http://dx.doi.org/10.1155/2022/3063965 |
| spellingShingle | Peipei Zhang Guokun Xie Jinsong Zhang Gaussian Function Fusing Fully Convolutional Network and Region Proposal-Based Network for Ship Target Detection in SAR Images International Journal of Antennas and Propagation |
| title | Gaussian Function Fusing Fully Convolutional Network and Region Proposal-Based Network for Ship Target Detection in SAR Images |
| title_full | Gaussian Function Fusing Fully Convolutional Network and Region Proposal-Based Network for Ship Target Detection in SAR Images |
| title_fullStr | Gaussian Function Fusing Fully Convolutional Network and Region Proposal-Based Network for Ship Target Detection in SAR Images |
| title_full_unstemmed | Gaussian Function Fusing Fully Convolutional Network and Region Proposal-Based Network for Ship Target Detection in SAR Images |
| title_short | Gaussian Function Fusing Fully Convolutional Network and Region Proposal-Based Network for Ship Target Detection in SAR Images |
| title_sort | gaussian function fusing fully convolutional network and region proposal based network for ship target detection in sar images |
| url | http://dx.doi.org/10.1155/2022/3063965 |
| work_keys_str_mv | AT peipeizhang gaussianfunctionfusingfullyconvolutionalnetworkandregionproposalbasednetworkforshiptargetdetectioninsarimages AT guokunxie gaussianfunctionfusingfullyconvolutionalnetworkandregionproposalbasednetworkforshiptargetdetectioninsarimages AT jinsongzhang gaussianfunctionfusingfullyconvolutionalnetworkandregionproposalbasednetworkforshiptargetdetectioninsarimages |