D-MFPN: A Doppler Feature Matrix Fused with a Multilayer Feature Pyramid Network for SAR Ship Detection
Ship detection from synthetic aperture radar (SAR) images has become a major research field in recent years. It plays a major role in monitoring the ocean, marine rescue activities, and marine safety warnings. However, there are still some factors that restrict further improvements in detecting perf...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/3/626 |
| _version_ | 1797623328864731136 |
|---|---|
| author | Yucheng Zhou Kun Fu Bing Han Junxin Yang Zongxu Pan Yuxin Hu Di Yin |
| author_facet | Yucheng Zhou Kun Fu Bing Han Junxin Yang Zongxu Pan Yuxin Hu Di Yin |
| author_sort | Yucheng Zhou |
| collection | DOAJ |
| description | Ship detection from synthetic aperture radar (SAR) images has become a major research field in recent years. It plays a major role in monitoring the ocean, marine rescue activities, and marine safety warnings. However, there are still some factors that restrict further improvements in detecting performance, e.g., multi-scale ship transformation and unfocused images caused by motion. In order to resolve these issues, in this paper, a doppler feature matrix fused with a multi-layer feature pyramid network (D-MFPN) is proposed for SAR ship detection. The D-MFPN takes single-look complex image data as input and consists of two branches: the image branch designs a multi-layer feature pyramid network to enhance the positioning capacity for large ships combined with an attention module to refine the feature map’s expressiveness, and the doppler branch aims to build a feature matrix that characterizes the ship’s motion state by estimating the doppler center frequency and frequency modulation rate offset. To confirm the validity of each branch, individual ablation experiments are conducted. The experimental results on the Gaofen-3 satellite ship dataset illustrate the D-MFPN’s optimal performance in defocused ship detection tasks compared with six other competitive convolutional neural network (CNN)-based SAR ship detectors. Its satisfactory results demonstrate the application value of the deep-learning model fused with doppler features in the field of SAR ship detection. |
| first_indexed | 2024-03-11T09:27:13Z |
| format | Article |
| id | doaj.art-65ec73c894ec4b6391c5890b8a1751ff |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T09:27:13Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-65ec73c894ec4b6391c5890b8a1751ff2023-11-16T17:51:55ZengMDPI AGRemote Sensing2072-42922023-01-0115362610.3390/rs15030626D-MFPN: A Doppler Feature Matrix Fused with a Multilayer Feature Pyramid Network for SAR Ship DetectionYucheng Zhou0Kun Fu1Bing Han2Junxin Yang3Zongxu Pan4Yuxin Hu5Di Yin6Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaShip detection from synthetic aperture radar (SAR) images has become a major research field in recent years. It plays a major role in monitoring the ocean, marine rescue activities, and marine safety warnings. However, there are still some factors that restrict further improvements in detecting performance, e.g., multi-scale ship transformation and unfocused images caused by motion. In order to resolve these issues, in this paper, a doppler feature matrix fused with a multi-layer feature pyramid network (D-MFPN) is proposed for SAR ship detection. The D-MFPN takes single-look complex image data as input and consists of two branches: the image branch designs a multi-layer feature pyramid network to enhance the positioning capacity for large ships combined with an attention module to refine the feature map’s expressiveness, and the doppler branch aims to build a feature matrix that characterizes the ship’s motion state by estimating the doppler center frequency and frequency modulation rate offset. To confirm the validity of each branch, individual ablation experiments are conducted. The experimental results on the Gaofen-3 satellite ship dataset illustrate the D-MFPN’s optimal performance in defocused ship detection tasks compared with six other competitive convolutional neural network (CNN)-based SAR ship detectors. Its satisfactory results demonstrate the application value of the deep-learning model fused with doppler features in the field of SAR ship detection.https://www.mdpi.com/2072-4292/15/3/626ship detectionsynthetic aperture radar (SAR) |
| spellingShingle | Yucheng Zhou Kun Fu Bing Han Junxin Yang Zongxu Pan Yuxin Hu Di Yin D-MFPN: A Doppler Feature Matrix Fused with a Multilayer Feature Pyramid Network for SAR Ship Detection Remote Sensing ship detection synthetic aperture radar (SAR) |
| title | D-MFPN: A Doppler Feature Matrix Fused with a Multilayer Feature Pyramid Network for SAR Ship Detection |
| title_full | D-MFPN: A Doppler Feature Matrix Fused with a Multilayer Feature Pyramid Network for SAR Ship Detection |
| title_fullStr | D-MFPN: A Doppler Feature Matrix Fused with a Multilayer Feature Pyramid Network for SAR Ship Detection |
| title_full_unstemmed | D-MFPN: A Doppler Feature Matrix Fused with a Multilayer Feature Pyramid Network for SAR Ship Detection |
| title_short | D-MFPN: A Doppler Feature Matrix Fused with a Multilayer Feature Pyramid Network for SAR Ship Detection |
| title_sort | d mfpn a doppler feature matrix fused with a multilayer feature pyramid network for sar ship detection |
| topic | ship detection synthetic aperture radar (SAR) |
| url | https://www.mdpi.com/2072-4292/15/3/626 |
| work_keys_str_mv | AT yuchengzhou dmfpnadopplerfeaturematrixfusedwithamultilayerfeaturepyramidnetworkforsarshipdetection AT kunfu dmfpnadopplerfeaturematrixfusedwithamultilayerfeaturepyramidnetworkforsarshipdetection AT binghan dmfpnadopplerfeaturematrixfusedwithamultilayerfeaturepyramidnetworkforsarshipdetection AT junxinyang dmfpnadopplerfeaturematrixfusedwithamultilayerfeaturepyramidnetworkforsarshipdetection AT zongxupan dmfpnadopplerfeaturematrixfusedwithamultilayerfeaturepyramidnetworkforsarshipdetection AT yuxinhu dmfpnadopplerfeaturematrixfusedwithamultilayerfeaturepyramidnetworkforsarshipdetection AT diyin dmfpnadopplerfeaturematrixfusedwithamultilayerfeaturepyramidnetworkforsarshipdetection |