A Deep Detection Network Based on Interaction of Instance Segmentation and Object Detection for SAR Images
Ship detection is a challenging task for synthetic aperture radar (SAR) images. Ships have arbitrary directionality and multiple scales in SAR images. Furthermore, there is a lot of clutter near the ships. Traditional detection algorithms are not robust to these situations and easily cause redundanc...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/13/2582 |
| _version_ | 1827688160014893056 |
|---|---|
| author | Zitong Wu Biao Hou Bo Ren Zhongle Ren Shuang Wang Licheng Jiao |
| author_facet | Zitong Wu Biao Hou Bo Ren Zhongle Ren Shuang Wang Licheng Jiao |
| author_sort | Zitong Wu |
| collection | DOAJ |
| description | Ship detection is a challenging task for synthetic aperture radar (SAR) images. Ships have arbitrary directionality and multiple scales in SAR images. Furthermore, there is a lot of clutter near the ships. Traditional detection algorithms are not robust to these situations and easily cause redundancy in the detection area. With the continuous improvement in resolution, the traditional algorithms cannot achieve high-precision ship detection in SAR images. An increasing number of deep learning algorithms have been applied to SAR ship detection. In this study, a new ship detection network, known as the instance segmentation assisted ship detection network (ISASDNet), is presented. ISASDNet is a two-stage detection network with two branches. A branch is called an object branch and can extract object-level information to obtain positioning bounding boxes and classification results. Another branch called the pixel branch can be utilized for instance segmentation. In the pixel branch, the designed global relational inference layer maps the features to interaction space to learn the relationship between ship and background. The global reasoning module (GRM) based on global relational inference layers can better extract the instance segmentation results of ships. A mask assisted ship detection module (MASDM) is behind the two branches. The MASDM can improve detection results by interacting with the outputs of the two branches. In addition, a strategy is designed to extract the mask of SAR ships, which enables ISASDNet to perform object detection training and instance segmentation training at the same time. Experiments carried out two different datasets demonstrated the superiority of ISASDNet over other networks. |
| first_indexed | 2024-03-10T09:50:00Z |
| format | Article |
| id | doaj.art-901b5567188240859ca2fa947d10832f |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T09:50:00Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-901b5567188240859ca2fa947d10832f2023-11-22T02:49:21ZengMDPI AGRemote Sensing2072-42922021-07-011313258210.3390/rs13132582A Deep Detection Network Based on Interaction of Instance Segmentation and Object Detection for SAR ImagesZitong Wu0Biao Hou1Bo Ren2Zhongle Ren3Shuang Wang4Licheng Jiao5The Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaThe Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaThe Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaThe Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaThe Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaThe Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaShip detection is a challenging task for synthetic aperture radar (SAR) images. Ships have arbitrary directionality and multiple scales in SAR images. Furthermore, there is a lot of clutter near the ships. Traditional detection algorithms are not robust to these situations and easily cause redundancy in the detection area. With the continuous improvement in resolution, the traditional algorithms cannot achieve high-precision ship detection in SAR images. An increasing number of deep learning algorithms have been applied to SAR ship detection. In this study, a new ship detection network, known as the instance segmentation assisted ship detection network (ISASDNet), is presented. ISASDNet is a two-stage detection network with two branches. A branch is called an object branch and can extract object-level information to obtain positioning bounding boxes and classification results. Another branch called the pixel branch can be utilized for instance segmentation. In the pixel branch, the designed global relational inference layer maps the features to interaction space to learn the relationship between ship and background. The global reasoning module (GRM) based on global relational inference layers can better extract the instance segmentation results of ships. A mask assisted ship detection module (MASDM) is behind the two branches. The MASDM can improve detection results by interacting with the outputs of the two branches. In addition, a strategy is designed to extract the mask of SAR ships, which enables ISASDNet to perform object detection training and instance segmentation training at the same time. Experiments carried out two different datasets demonstrated the superiority of ISASDNet over other networks.https://www.mdpi.com/2072-4292/13/13/2582synthetic aperture radar (SAR)object detectionconvolutional neural network (CNN)instance segmentation |
| spellingShingle | Zitong Wu Biao Hou Bo Ren Zhongle Ren Shuang Wang Licheng Jiao A Deep Detection Network Based on Interaction of Instance Segmentation and Object Detection for SAR Images Remote Sensing synthetic aperture radar (SAR) object detection convolutional neural network (CNN) instance segmentation |
| title | A Deep Detection Network Based on Interaction of Instance Segmentation and Object Detection for SAR Images |
| title_full | A Deep Detection Network Based on Interaction of Instance Segmentation and Object Detection for SAR Images |
| title_fullStr | A Deep Detection Network Based on Interaction of Instance Segmentation and Object Detection for SAR Images |
| title_full_unstemmed | A Deep Detection Network Based on Interaction of Instance Segmentation and Object Detection for SAR Images |
| title_short | A Deep Detection Network Based on Interaction of Instance Segmentation and Object Detection for SAR Images |
| title_sort | deep detection network based on interaction of instance segmentation and object detection for sar images |
| topic | synthetic aperture radar (SAR) object detection convolutional neural network (CNN) instance segmentation |
| url | https://www.mdpi.com/2072-4292/13/13/2582 |
| work_keys_str_mv | AT zitongwu adeepdetectionnetworkbasedoninteractionofinstancesegmentationandobjectdetectionforsarimages AT biaohou adeepdetectionnetworkbasedoninteractionofinstancesegmentationandobjectdetectionforsarimages AT boren adeepdetectionnetworkbasedoninteractionofinstancesegmentationandobjectdetectionforsarimages AT zhongleren adeepdetectionnetworkbasedoninteractionofinstancesegmentationandobjectdetectionforsarimages AT shuangwang adeepdetectionnetworkbasedoninteractionofinstancesegmentationandobjectdetectionforsarimages AT lichengjiao adeepdetectionnetworkbasedoninteractionofinstancesegmentationandobjectdetectionforsarimages AT zitongwu deepdetectionnetworkbasedoninteractionofinstancesegmentationandobjectdetectionforsarimages AT biaohou deepdetectionnetworkbasedoninteractionofinstancesegmentationandobjectdetectionforsarimages AT boren deepdetectionnetworkbasedoninteractionofinstancesegmentationandobjectdetectionforsarimages AT zhongleren deepdetectionnetworkbasedoninteractionofinstancesegmentationandobjectdetectionforsarimages AT shuangwang deepdetectionnetworkbasedoninteractionofinstancesegmentationandobjectdetectionforsarimages AT lichengjiao deepdetectionnetworkbasedoninteractionofinstancesegmentationandobjectdetectionforsarimages |